Paper Citation Record · LEDGER

The Linear Representation Hypothesis and the Geometry of Large Language Models

As of 4 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 100 inbound Pith citation observations for arXiv:2311.03658.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2311.03658 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T21:43:28.274354Z

measured 130 of 130 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 100 of 115 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T06:52:33.560287Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T08:06:57.505025Z

Reference resolution

30 of 30 outbound references displayed

verified exact12
verified fuzzy7
unresolved1
parse uncertain0
malformed identifier2
metadata mismatch8

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b291ee5-aba1-49fd-8bed-a4ea8b04afb2 · outbound

This paper cites doi: 10.18653/v1/K16-1002.

The Linear Representation Hypothesis and the Geometry of Large Language Models doi: 10.18653/v1/K16-1002

Reference 1

Resolution: verified exact; doi, observed 2026-05-11T21:43:28.479284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 59da1787-bffc-46fe-a284-a36f659f8989 · outbound

This paper cites Word embed- dings, analogies, and machine learning: Beyond king - man + woman = queen.

The Linear Representation Hypothesis and the Geometry of Large Language Models Word embed- dings, analogies, and machine learning: Beyond king - man + woman = queen

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.657707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 139852d6-5f16-49b1-8129-f853edff6f0f · outbound

This paper cites Toy Models of Superposition.

The Linear Representation Hypothesis and the Geometry of Large Language Models Toy Models of Superposition

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:44:43.591728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2eb12af5-2144-4030-bdfd-700c545b20b4 · outbound

This paper cites How contextual are contextualized word rep- resentations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings.

The Linear Representation Hypothesis and the Geometry of Large Language Models How contextual are contextualized word rep- resentations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.983047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5d9b42c9-1c1e-408b-ad0d-36a63aaa6b43 · outbound

This paper cites doi: 10.18653/v1/2020.conll-1.29.

The Linear Representation Hypothesis and the Geometry of Large Language Models doi: 10.18653/v1/2020.conll-1.29

Reference 5

Resolution: verified exact; doi, observed 2026-05-11T21:43:28.398351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 73ac30ff-3418-465e-977b-fc03e3bcb8fb · outbound

This paper cites word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method.

The Linear Representation Hypothesis and the Geometry of Large Language Models word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:29.106125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b70add9d-6238-4c47-874f-d30dbc1aa402 · outbound

This paper cites Language Models Represent Space and Time.

The Linear Representation Hypothesis and the Geometry of Large Language Models Language Models Represent Space and Time

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:29.286219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ce24123d-0066-4226-8ef1-7b6c1484205e · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

The Linear Representation Hypothesis and the Geometry of Large Language Models Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 8

Resolution: malformed identifier; doi_truncated, observed 2026-05-11T21:43:28.384341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2f66244f-e0aa-4763-84c8-8810b9079ce0 · outbound

This paper cites Linearity of Relation Decoding in Transformer Language Models.

The Linear Representation Hypothesis and the Geometry of Large Language Models Linearity of Relation Decoding in Transformer Language Models

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:29.613574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1f28caa4-b08f-45e7-a03d-fe1595362419 · outbound

This paper cites and Manning, C.

The Linear Representation Hypothesis and the Geometry of Large Language Models and Manning, C

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.825099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e5ac71da-5dce-47a6-9c96-933c35c48abc · outbound

This paper cites Towards a Definition of Disentangled Representations.

The Linear Representation Hypothesis and the Geometry of Large Language Models Towards a Definition of Disentangled Representations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:29.799241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bde047bf-2200-4227-975c-9c3ecef51bff · outbound

This paper cites Uncovering Meanings of Embeddings via Partial Orthogonality.

The Linear Representation Hypothesis and the Geometry of Large Language Models Uncovering Meanings of Embeddings via Partial Orthogonality

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:28.529829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 94fc5493-400a-48fa-8026-96b0d6b638cc · outbound

This paper cites and Richardson, J.

The Linear Representation Hypothesis and the Geometry of Large Language Models and Richardson, J

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.461359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ee44ab7-bb78-4191-85bf-137bba54e2e9 · outbound

This paper cites On the sentence embeddings from pre-trained language mod- els.

The Linear Representation Hypothesis and the Geometry of Large Language Models On the sentence embeddings from pre-trained language mod- els

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.126401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b371db0-ad76-4b87-87b5-b8032b97ddfe · outbound

This paper cites Language Models Implement Simple Word2Vec-style Vector Arithmetic.

The Linear Representation Hypothesis and the Geometry of Large Language Models Language Models Implement Simple Word2Vec-style Vector Arithmetic

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:30.950053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7780770e-ccd5-43fb-af23-3c390be32f67 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

The Linear Representation Hypothesis and the Geometry of Large Language Models Gemma: Open Models Based on Gemini Research and Technology

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:43:28.655030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 320fbbd9-934e-4dc4-b3c4-4975a45feb24 · outbound

This paper cites Exploiting Similarities among Languages for Machine Translation.

The Linear Representation Hypothesis and the Geometry of Large Language Models Exploiting Similarities among Languages for Machine Translation

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:30.169358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fa8657d3-6414-4f4e-b038-c76591100e3d · outbound

This paper cites In: Zong, C., Xia, F., Li, W., Navigli, R.

The Linear Representation Hypothesis and the Geometry of Large Language Models In: Zong, C., Xia, F., Li, W., Navigli, R

Reference 18

Resolution: malformed identifier; doi_truncated, observed 2026-05-11T21:43:28.408352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0dc38bc-ecfa-4dea-9fb9-9239c66a953c · outbound

This paper cites Identifiable Deep Generative Models via Sparse Decoding.

The Linear Representation Hypothesis and the Geometry of Large Language Models Identifiable Deep Generative Models via Sparse Decoding

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:28.460391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ca4d0cb6-e414-48b2-beb1-8d30f6ae2887 · outbound

This paper cites GPT-4 Technical Report.

The Linear Representation Hypothesis and the Geometry of Large Language Models GPT-4 Technical Report

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:43:30.388356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 867166c8-2275-45a9-add2-7de59268118d · outbound

This paper cites URL https://openreview.

The Linear Representation Hypothesis and the Geometry of Large Language Models URL https://openreview

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:32.325812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 40c7b21f-0bf3-48fb-a661-2273ee78ec1d · outbound

This paper cites Prompt Algebra for Task Composition.

The Linear Representation Hypothesis and the Geometry of Large Language Models Prompt Algebra for Task Composition

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:30.488509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 202e8ce7-6c0d-459e-aed9-a859c14d2f6b · outbound

This paper cites Function Vectors in Large Language Models.

The Linear Representation Hypothesis and the Geometry of Large Language Models Function Vectors in Large Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:30.555364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad5c94e6-087d-42ad-bfd6-2eb020aff112 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

The Linear Representation Hypothesis and the Geometry of Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:43:30.571363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3d82047f-a36f-4353-98db-ab8a0640b6df · outbound

This paper cites Steering Language Models With Activation Engineering.

The Linear Representation Hypothesis and the Geometry of Large Language Models Steering Language Models With Activation Engineering

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:43:30.686612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 23022202-2321-4d70-8fa6-f80c3e6b02bc · outbound

This paper cites Steering Language Models With Activation Engineering.

The Linear Representation Hypothesis and the Geometry of Large Language Models Steering Language Models With Activation Engineering

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:43:28.434370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4ea8c1a5-1610-4c6c-96b1-7f4b56bd68bc · outbound

This paper cites Concept Algebra for (Score-Based) Text-Controlled Generative Models.

The Linear Representation Hypothesis and the Geometry of Large Language Models Concept Algebra for (Score-Based) Text-Controlled Generative Models

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:30.714159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c909f869-1d84-4ec2-aab2-17f6a6155805 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

The Linear Representation Hypothesis and the Geometry of Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:43:30.838860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 123ff599-073d-4de6-8831-5b8065b324d0 · outbound

This paper cites an unresolved cited work.

The Linear Representation Hypothesis and the Geometry of Large Language Models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-11T21:43:32.176975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c8e59e2b-90a9-4867-ac88-5f1606c37bbd · outbound

This paper cites princess.

The Linear Representation Hypothesis and the Geometry of Large Language Models princess

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T21:43:31.315155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation a23b6ff5-9f92-4ad3-98d4-57caf4a1a8aa · inbound

Steering Language Models With Activation Engineering cites this paper.

Steering Language Models With Activation Engineering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 145

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7dad1e21-0e1b-44cc-9fda-6a8dd0eb9cba · inbound

Steering Llama 2 via Contrastive Activation Addition cites this paper.

Steering Llama 2 via Contrastive Activation Addition The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b74b5573-4857-4de3-90eb-0a10113c9e6b · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 169

Resolution: verified exact; local_arxiv, observed 2026-05-13T10:47:56.070911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cec1f0c9-4926-49c0-8b39-c03b62292513 · inbound

ActivationReasoning: Logical Reasoning in Latent Activation Spaces cites this paper.

ActivationReasoning: Logical Reasoning in Latent Activation Spaces The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-18T05:45:56.267867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dae0339d-8035-47f8-a800-a8cb9e6a0694 · inbound

Latent Collaboration in Multi-Agent Systems cites this paper.

Latent Collaboration in Multi-Agent Systems The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T20:17:50.908815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac109eb0-4e4b-4609-8fcc-d53f164d0855 · inbound

Latent Collaboration in Multi-Agent Systems cites this paper.

Latent Collaboration in Multi-Agent Systems The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T06:52:33.560287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda913ad-7c3f-4d9c-9f53-58af601edf1b · inbound

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models cites this paper.

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T09:31:52.222463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8a31ab0-0a2c-45b8-b405-ce4507d740ba · inbound

Representation Unlearning: Forgetting through Information Compression cites this paper.

Representation Unlearning: Forgetting through Information Compression The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T06:59:18.694969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95aea746-5aa4-4e0b-9ce1-97e589d064fa · inbound

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models cites this paper.

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 238

Resolution: unresolved; no resolver link, observed 2026-08-03T04:41:08.934459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef61d8b1-a38e-49e8-9f28-e97f159c5df1 · inbound

Symmetry in language statistics shapes the geometry of model representations cites this paper.

Symmetry in language statistics shapes the geometry of model representations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T23:03:51.964030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b803c4-9940-4ab6-8f79-cf710006c452 · inbound

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems cites this paper.

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T22:58:09.905242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ee2064-937c-41fb-babb-b109533356fa · inbound

Transformers converge to invariant algorithmic cores cites this paper.

Transformers converge to invariant algorithmic cores The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T20:46:32.212954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9062e3-7f11-41c8-82b9-9e97557a975f · inbound

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs cites this paper.

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T17:47:09.080741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3c1119f-cf64-4743-bb4f-9705252d9796 · inbound

Dual Implications of Quark Mass Hierarchies to Flavor Structure cites this paper.

Dual Implications of Quark Mass Hierarchies to Flavor Structure The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T13:46:54.451163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04dc092f-c75e-4b09-ba49-bd99f473c4e9 · inbound

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens cites this paper.

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-13T21:03:20.273417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4967cd14-5205-4c38-b8c6-aed4c8badd51 · inbound

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment cites this paper.

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35ad8043-8764-4fe5-9baa-93a5fb64ef1d · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de737fb7-c079-4d8d-8083-00d3cbb2e2b8 · inbound

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds cites this paper.

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 670c224a-cd5f-4c9d-80ac-a35546c2b3b6 · inbound

From Weights to Activations: Is Steering the Next Frontier of Adaptation? cites this paper.

From Weights to Activations: Is Steering the Next Frontier of Adaptation? The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation aa64e0dd-4a38-422e-b080-4e8815045beb · inbound

Rhetorical Questions in LLM Representations: A Linear Probing Study cites this paper.

Rhetorical Questions in LLM Representations: A Linear Probing Study The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c4a25f7e-d1f8-489b-acef-4943017984d2 · inbound

Characterizing Model-Native Skills cites this paper.

Characterizing Model-Native Skills The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 95ba164b-e9b8-4273-83dc-726ed179b39c · inbound

LLM Safety From Within: Detecting Harmful Content with Internal Representations cites this paper.

LLM Safety From Within: Detecting Harmful Content with Internal Representations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2616ca12-309c-4461-8f7a-a4cc39749ccd · inbound

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams cites this paper.

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e708406c-f2d7-41af-bf94-dcaabdb17a7b · inbound

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams cites this paper.

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-12T00:51:15.470272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e11ef6b7-b56c-4ec7-a3a9-90cb8b7aa2a4 · inbound

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control cites this paper.

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 90

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc29f0a8-4bd8-4818-8d2e-64d5f513370d · inbound

Cell-Based Representation of Relational Binding in Language Models cites this paper.

Cell-Based Representation of Relational Binding in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 84eddc99-ec13-417f-a46a-ffea433a7725 · inbound

There Will Be a Scientific Theory of Deep Learning cites this paper.

There Will Be a Scientific Theory of Deep Learning The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 205

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a25da2ea-32c5-4254-a9b7-ad36e1a76a6f · inbound

Semantic Structure of Feature Space in Large Language Models cites this paper.

Semantic Structure of Feature Space in Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-12T09:41:26.823231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2eee559c-0cb6-4b8f-b2e1-9eefcd974d50 · inbound

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models cites this paper.

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4688a4db-c291-4465-8783-9c54b9c65f29 · inbound

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models cites this paper.

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 139fa3dd-149c-40ed-b1cd-af9924354e77 · inbound

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis cites this paper.

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2064b23c-58ca-425a-91f7-a5523d338ef2 · inbound

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis cites this paper.

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T14:57:40.433348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fffd8e2-ad41-4d9d-8b58-5cd8bc6bcdc0 · inbound

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It cites this paper.

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T23:16:14.397776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fc341478-53ef-4751-85db-7f569135db08 · inbound

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It cites this paper.

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T17:02:40.952806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 915c587a-1a33-44cd-8844-10a86ab36911 · inbound

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior cites this paper.

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 204

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35d870f2-e82e-41f3-9186-54527ecf892b · inbound

SLAM: Structural Linguistic Activation Marking for Language Models cites this paper.

SLAM: Structural Linguistic Activation Marking for Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 17f064e3-2fc1-4414-8bdf-78a0ebcd2d1e · inbound

Negative Before Positive: Asymmetric Valence Processing in Large Language Models cites this paper.

Negative Before Positive: Asymmetric Valence Processing in Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4c38d43e-fc15-4c47-88e8-e7307d67e265 · inbound

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 910488ed-2c93-4e9a-8e62-f61b379587e9 · inbound

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models cites this paper.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 18a2f92f-5d4c-436d-a1c7-161da414cf17 · inbound

Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer cites this paper.

Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f90385e2-d43e-4059-9a7f-b5266057ef43 · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c9fe748b-52cf-4888-870c-7843fdb64592 · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-12T07:16:25.588628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3ef5758f-92bb-4d15-a9a5-cf6bfd75041c · inbound

Tool Calling is Linearly Readable and Steerable in Language Models cites this paper.

Tool Calling is Linearly Readable and Steerable in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d1945439-772a-4b8d-bc34-4abea36928c9 · inbound

A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases cites this paper.

A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-12T07:41:42.941144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 609bdab7-bbdf-44f0-bd16-0144a3d441b1 · inbound

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations cites this paper.

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-12T01:56:14.645755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 65beeffb-046c-49df-8417-da6bb053262d · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 86

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T05:22:18.937236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 57f125bb-685a-40f3-aede-079bce55a65a · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 248

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T20:19:27.594213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 275efe12-4cf1-4d26-bd85-3f3a41ea530e · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-14T20:19:26.786402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 597e33c4-d517-464c-b999-b0277e71b721 · inbound

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models cites this paper.

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:23:40.838965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2cb2019f-0763-433d-bd58-e915ceb50f53 · inbound

Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models cites this paper.

Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T09:34:05.537405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 88613cef-fa31-4319-a116-428c086be6ad · inbound

Interpretable Discriminative Text Representations via Agreement and Label Disentanglement cites this paper.

Interpretable Discriminative Text Representations via Agreement and Label Disentanglement The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:49:41.181018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 58dccf39-689d-47f5-9940-c009f94f1281 · inbound

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering cites this paper.

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T06:54:01.061064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a9b068d6-4886-475c-9ba8-c4eb9db697d0 · inbound

Manifold-Guided Attention Steering cites this paper.

Manifold-Guided Attention Steering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:14:45.325447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b170795-452a-49ba-80c9-ba3f5cdc3448 · inbound

Relational Linear Properties in Language Models: An Empirical Investigation cites this paper.

Relational Linear Properties in Language Models: An Empirical Investigation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:46:15.018582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fbd9cc56-5f78-470f-801c-da71142a444b · inbound

Relational Linear Properties in Language Models: An Empirical Investigation cites this paper.

Relational Linear Properties in Language Models: An Empirical Investigation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:14:56.771525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0a18c7c3-2870-4403-883e-9083d9291878 · inbound

Steered Generation via Gradient-Based Optimization on Sparse Query Features cites this paper.

Steered Generation via Gradient-Based Optimization on Sparse Query Features The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-25T05:36:40.368644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e975a75d-4fdb-4d05-8db2-e7193cb03228 · inbound

Is Dimensionality a Barrier for Retrieval Models? cites this paper.

Is Dimensionality a Barrier for Retrieval Models? The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 149

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T04:56:38.696798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation aa965ec7-c55b-4aef-ad97-9e94c01b1b06 · inbound

Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol cites this paper.

Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T14:14:45.880568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2b4e3898-8faa-4cf1-9481-72458d6dd13d · inbound

Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering cites this paper.

Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T12:04:38.994950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6181060e-1921-4dbd-a57e-82bdec59132e · inbound

When Does LeJEPA Learn a World Model? cites this paper.

When Does LeJEPA Learn a World Model? The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-01T16:55:50.666729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7981c700-95ae-4dd7-86d9-ec25e41fde30 · inbound

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling cites this paper.

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T18:13:48.589203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d0929d2-c988-4d99-962e-eec963be4218 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-29T14:23:30.791494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b319be0b-64ce-413e-aa60-61b52985f43e · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.284750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef325484-3056-407e-b869-49d8fa61fffe · inbound

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection cites this paper.

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-06-29T14:03:29.922065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 829ba2f1-19b1-4438-858d-459a4bae075c · inbound

Task-Focused Memorization for Multimodal Agents cites this paper.

Task-Focused Memorization for Multimodal Agents The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.464781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3e31525d-9b58-4224-83d2-e35f7dba91bd · inbound

Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models cites this paper.

Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T22:32:44.257595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 66b85099-2e87-43a7-ac1a-d577b5f808b6 · inbound

The Latin Substrate: How Language Models Represent and Mediate Script Choice cites this paper.

The Latin Substrate: How Language Models Represent and Mediate Script Choice The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T22:42:46.649576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e7089f7-a799-4d68-b59d-cf80d62692dc · inbound

How can embedding models bind concepts? cites this paper.

How can embedding models bind concepts? The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T19:16:00.012249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0e070daa-608f-46b3-8f11-60eb6d67ec57 · inbound

Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing cites this paper.

Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:09:58.297404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 11e18a58-c3ee-45c8-8f3d-ee47294c558d · inbound

Subliminal Learning is a LoRA Artifact cites this paper.

Subliminal Learning is a LoRA Artifact The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T20:42:37.580046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8163d568-2b86-4556-ba92-d1e0c3f4af55 · inbound

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete cites this paper.

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T22:06:16.191638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 79c191c8-ee28-405e-9176-a5d2d3434f78 · inbound

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization cites this paper.

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:26.233481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cf34da5f-1000-4bac-ab56-39fd7aa3ffdd · inbound

Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control cites this paper.

Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:56:44.417828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 81efa166-54bc-4547-878d-fc4acb51da66 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-07-01T14:05:47.167187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ca8345c1-b131-4988-8596-bbac718261f4 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-12T17:03:44.315006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b5f2a8-692a-4256-bbcc-e7ab790baf8e · inbound

LLM Self-Recognition: Steering and Retrieving Activation Signatures cites this paper.

LLM Self-Recognition: Steering and Retrieving Activation Signatures The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-06-28T01:41:29.220102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 48bfe687-9a5d-4e44-8780-1a0fe413510b · inbound

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders cites this paper.

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:47:09.905677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a953c807-3b93-44dc-9f3e-8717f7d96f21 · inbound

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs cites this paper.

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T20:47:23.503648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4e17a69d-bf00-46f1-b2e9-50d833b9900e · inbound

Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes cites this paper.

Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.330325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5704963c-5e68-4ef0-90ed-aa87e9f1a0cb · inbound

MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents cites this paper.

MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 63

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T04:57:38.170270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad25ba07-8be1-4010-b3ad-71b792f2ee32 · inbound

Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning cites this paper.

Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T04:47:38.169243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c6fcd92f-921f-4cb3-baa6-e1144320e9ca · inbound

Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics cites this paper.

Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-27T11:00:50.742498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cb9c84ab-85fa-409b-be4b-81790dcd9e97 · inbound

ICA Lens: Interpreting Language Models Without Training Another Dictionary cites this paper.

ICA Lens: Interpreting Language Models Without Training Another Dictionary The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:17:49.074333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3e32b1d5-b5eb-457f-a7b8-a6d712f603df · inbound

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models cites this paper.

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T11:18:03.826075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4ba5a90-f057-4cf7-a4e6-6cabc638e0aa · inbound

Size Doesn't Matter: Cosine-Scored Sparse Autoencoders cites this paper.

Size Doesn't Matter: Cosine-Scored Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-01T07:15:29.610244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4845f96e-2772-4d98-a9d7-a950b195e38d · inbound

When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations cites this paper.

When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T17:18:44.310765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 12abe38b-a151-41f7-b991-bf02f57a1c64 · inbound

Rift: A Conflict Signature for Deception in Language Models cites this paper.

Rift: A Conflict Signature for Deception in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:58:47.362857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32bc7fa4-3807-4e25-9cfc-1be225b50e42 · inbound

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cites this paper.

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 123

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T08:57:48.268939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 93128e0e-a720-4c8a-a982-4b06d493de17 · inbound

Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation cites this paper.

Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T02:19:22.977575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1beceb04-8240-4a5b-acbd-57d62e145a6e · inbound

Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation cites this paper.

Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:29:44.968692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f421c7ad-12bb-416b-9004-cb190da52066 · inbound

Abstract representational geometry supports inference in large language models cites this paper.

Abstract representational geometry supports inference in large language models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-26T08:49:15.521416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2040b22f-d453-488b-a4ee-52057ae579c6 · inbound

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization cites this paper.

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-26T01:28:50.539297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ccc076b5-5f50-43bb-b378-ac5ee9d003e8 · inbound

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models cites this paper.

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:55:40.750817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7c9f8f0d-291f-4eac-82f6-f3395d34cc87 · inbound

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale cites this paper.

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T07:33:43.015966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08db648d-2a05-48c2-9ed2-be53b65017d1 · inbound

The Objective Decides: When a Learned Dynamics Model Uses a Conserved Quantity cites this paper.

The Objective Decides: When a Learned Dynamics Model Uses a Conserved Quantity The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-12T00:22:10.213108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72362f9-aabc-4a52-90ab-a13c1c5e07b7 · inbound

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling cites this paper.

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T19:24:48.899301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89446ff8-e9d0-497c-a6f2-99c8bdc918c5 · inbound

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation cites this paper.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 681f66cb-41e1-4e9e-af5e-1fa4006353f2 · inbound

Dissociating the Internal Representations of Sycophancy in LLMs cites this paper.

Dissociating the Internal Representations of Sycophancy in LLMs The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T08:11:40.699123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a474e3-88ee-4278-bf52-d259e6c03d86 · inbound

Riemannian Geometry for Pre-trained Language Model Embeddings cites this paper.

Riemannian Geometry for Pre-trained Language Model Embeddings The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-09T21:16:34.244246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6123b0d0-a774-466e-b719-d10835bdddba · inbound

Prompt Compression via Activation Aggregation cites this paper.

Prompt Compression via Activation Aggregation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-10T08:06:57.506266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.