Pith. sign in

Paper Citation Record · LEDGER

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 3 inbound Pith citation observations for arXiv:2505.21800.

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

pith.paper-citation-record.v1
2505.21800 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:28:02.896098Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:01:47.847228Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

40 of 40 outbound references displayed

  • verified exact0
  • verified fuzzy12
  • unresolved28
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a3f445fb-28fa-4a33-a1b1-5ef0ae9d4ac0 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Understanding intermediate layers using linear classifier probes

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:59.847789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:27:59.847789Z digest=sha256:3bcece56e540c6db9f753f5a8e9aa01fa6bee533dd713cec8623c89c90111eed

Observation 04ea8199-8400-4fc9-8941-c6a83134ec4e · outbound

This paper cites Refusal in language models is mediated by a single direction.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Refusal in language models is mediated by a single direction

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.814272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:27:59.950402Z digest=sha256:bb46140d4520d2385d3a0ec37eb6e223ca16d22a645fd860ec2e5a356b4b87d5

Observation c6c2acd4-5291-4e4c-b9fd-6709abd76870 · outbound

This paper cites The Internal State of an LLM Knows When It's Lying.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs The Internal State of an LLM Knows When It's Lying

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.057643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.057643Z digest=sha256:abe5c7f77053561eb9bd76c94024d03512b23dad938ad8faa4619d3518e492dc

Observation ace53ab5-3a7b-4301-9a5c-d2e4c154bbc1 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Probing classifiers: Promises, shortcomings, and advances

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.706903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:00.153974Z digest=sha256:16b09a17484c1c64cfe82b68d346adbb8d3675d9d0dc3f8ef3409977860eea3d

Observation 0078724c-dbbf-45b1-9ae4-2bb508860bee · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Mechanistic Interpretability for AI Safety -- A Review

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.211642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.211642Z digest=sha256:c95121fbe76841e5cd72b19761d14a83608f54ef3d34dc9753aa41b60cebeecc

Observation b69bf6c7-8d5b-4304-9614-16b029e23e91 · outbound

This paper cites Language models are few-shot learners.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Language models are few-shot learners

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.493475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:00.262504Z digest=sha256:c42a69b523f9e95ed4647cd554ef5188dbf29a2143c90e68bdf33693ebea4933

Observation 81b65b78-40d9-4935-942f-cae148cbe40c · outbound

This paper cites Truth is Universal: Robust Detection of Lies in LLMs.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Truth is Universal: Robust Detection of Lies in LLMs

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.302815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.302815Z digest=sha256:07f85eaca0b7b0007030b67d91fd872fb24f40a2e5070b9f43b36d8a7fad6846

Observation 47991700-91e9-4e72-a7a8-5e1b57044454 · outbound

This paper cites an unresolved cited work.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.391564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.391564Z digest=sha256:8e7cfd407b04a07e7512b15f1d2b5c452e06eeccb8278638cf7dfa531f07983d

Observation 150ca2d8-b181-44ed-bc01-89d9371d6a02 · outbound

This paper cites C., Lundberg, S.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs C., Lundberg, S

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.514448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.514448Z digest=sha256:6671cea221f70b0e76d30f02e22e06ea2676f8130f67a4f043a07e0b68fed242

Observation 8307d388-da22-4023-bb8a-0b27a7263393 · outbound

This paper cites From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.576395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.576395Z digest=sha256:1c3fbd4cf2b57710306669fb84164370973d0cf010415e28a246382598fea02d

Observation 2d62b86c-66df-4e49-8179-8f6d8daeb7ab · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.629640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.629640Z digest=sha256:b5745357bb16266b6bea366d33e116f69cea114304deac823679e5ad11ce85b0

Observation 879689ee-382a-4dd8-8543-74caa120033b · outbound

This paper cites Toy Models of Superposition.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Toy Models of Superposition

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.704798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.704798Z digest=sha256:04321218410f8f2a6c899485a393067a75bc6b44d47fe026dabe795d0f70cbb6

Observation 44a87f73-8562-4a2b-98f8-8fb523dc1847 · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Not All Language Model Features Are One-Dimensionally Linear

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.819179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.819179Z digest=sha256:d881af4869e1666b5b9e885b820f2b1adf01b74ba620c7a7a127578b8c36ffce

Observation b640db2b-7daf-4a19-9da9-e08abb8412bc · outbound

This paper cites Sequential integrated gradients: A simple but effective method for explaining language models.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Sequential integrated gradients: A simple but effective method for explaining language models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:00.901866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:00.901866Z digest=sha256:f567a4c24a6456a96cd4dd244e60479b9f4509290262b71a23834212e89a7e89

Observation 45f21513-9c7a-4bc1-a9ee-dca34c421494 · outbound

This paper cites and Tegmark, M.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs and Tegmark, M

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.351687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:00.957040Z digest=sha256:f046d4719cd67baaab191cd3c45ce9c618b2d7b3fdcd6e42b3bba57d86e92b1a

Observation bec5cdc0-ee92-4958-b014-b4345c467e14 · outbound

This paper cites X-Risk Analysis for AI Research.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs X-Risk Analysis for AI Research

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.051898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.051898Z digest=sha256:40a3a4cfd2d7332d4eb800ba3b63bffdec78585f5334f3a01d4365ae4e2b0e2a

Observation 7d2c3955-327f-44b5-88eb-8603bc507b99 · outbound

This paper cites An Overview of Catastrophic AI Risks.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs An Overview of Catastrophic AI Risks

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.117390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.117390Z digest=sha256:ce873f5a14c2b8d674d6f785c5c628e3825b1971748bd9247a2edad15b75cb74

Observation 189a364b-e6a2-44fa-ad62-842051410f85 · outbound

This paper cites Do LLMs "know" internally when they follow instructions?.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Do LLMs "know" internally when they follow instructions?

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.184746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.184746Z digest=sha256:be9ee99a472edb1d5e1c1b5d69ed9e8e7dfc329c3ab5fe1fbee62312e5117aaf

Observation c1e00696-6307-4123-8077-4a8cfe9e000c · outbound

This paper cites and Manning, C.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs and Manning, C

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.280948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.280948Z digest=sha256:d9b031d335e9b6fe6fee0b685d84931a0520556b9d0a7861fecf2de01cf65c08

Observation 20956f71-d4aa-4f50-a5e4-5565a7e8d1a0 · outbound

This paper cites Refusal Behavior in Large Language Models: A Nonlinear Perspective.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Refusal Behavior in Large Language Models: A Nonlinear Perspective

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.376676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.376676Z digest=sha256:c665accf3eadf8633e3d845f930401c20542b9e9794eed65e6b9da1e6cf73e01

Observation 3adb0171-8940-4338-af2c-280c251ded82 · outbound

This paper cites Linear representations of political perspective emerge in large language models.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Linear representations of political perspective emerge in large language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.198168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:01.464820Z digest=sha256:14787a3987a3a134351e515842b6c284671e2d38a13975737114410594cca004

Observation 6be96987-204d-4e99-bb48-22ea76ceb463 · outbound

This paper cites Generating Wikipedia by Summarizing Long Sequences.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Generating Wikipedia by Summarizing Long Sequences

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.546143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.546143Z digest=sha256:66209a6984e6a6187a1f970cb4d0882484b178ec2ab63af1e7ee179479e29f1f

Observation 7521b11d-60ca-42cf-b55c-9cb52c43d05b · outbound

This paper cites Cones: Concept Neurons in Diffusion Models for Customized Generation.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Cones: Concept Neurons in Diffusion Models for Customized Generation

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.636198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.636198Z digest=sha256:47caadbb2456af47e329318eeb98d21a6d0ecb30aea0d23a65065c9dfc5d4f2b

Observation 534da651-1afe-434e-94d6-4f91f0eed78a · outbound

This paper cites and Tegmark, M.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs and Tegmark, M

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:05.039213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:01.723307Z digest=sha256:51b917fc76de3ee809ea8b7b0499f986ab4105b98829815ee7dd263414968a87

Observation 31bef590-c80b-4d06-a4c4-dc138bf82863 · outbound

This paper cites Linguistic regularities in continuous space word representations.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Linguistic regularities in continuous space word representations

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:04.845890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:01.764167Z digest=sha256:d9fa6e74354328e596fe4392d9aa4d50f9989bb19bff3914e3dffb55c1f0f725

Observation 7ff1b04c-c0e8-4365-9969-ff6cb2bf4baf · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Progress measures for grokking via mechanistic interpretability

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.830836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.830836Z digest=sha256:584f880af614bef83821a4c80877a946ff0f098bbf06e7c1c6147a4f973bc11e

Observation 69e0e3d4-2040-4c0b-8b68-1c21e8c6a2e8 · outbound

This paper cites The Alignment Problem from a Deep Learning Perspective.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs The Alignment Problem from a Deep Learning Perspective

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.897413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.897413Z digest=sha256:bb7a897af50296402effbf86d8cb051ba57350a7d9019a3b7a35c489feba5775

Observation 3f14723c-d7dd-4310-8bdf-9fe7907fc36c · outbound

This paper cites Zoom in: An introduction to circuits.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Zoom in: An introduction to circuits

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:01.971422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:01.971422Z digest=sha256:0630f331aa64f6f2565956e682881aae88370223ba83588289d4a98443427b1c

Observation 280d9657-6672-4751-aa26-de164f877fec · outbound

This paper cites Introducing chatgpt.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Introducing chatgpt

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:04.603896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.080909Z digest=sha256:1c1566c9432df054277314937880b09298083f7eacf49cc1144a503d93a07c10

Observation c182496d-3a5d-4581-bbbb-3a7b3b4b7f8a · outbound

This paper cites GPT-4 Technical Report.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs GPT-4 Technical Report

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.152213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.152213Z digest=sha256:92767215980966eb48a84f763c79c660f95dd7590a983917d63a6b7a4a362672

Observation b880fcf9-89e8-40eb-98bf-2124960c0a40 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Steering Llama 2 via Contrastive Activation Addition

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.231534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.231534Z digest=sha256:517d1297e8f0c830f87c3d8ac951defd64a90a1d4565599c1b50c7e96c8c7dfb

Observation b2b3b2bd-9093-41ae-885c-7e3d3ad3923b · outbound

This paper cites J., and Veitch, V.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs J., and Veitch, V

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:04.344325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.318840Z digest=sha256:1b759669693da2e75f0895fcc543eedf479668d657289dca43ca2a230a8a2e76

Observation 6fe8b3b4-6cf5-4d74-8ba9-d3f3299f07a6 · outbound

This paper cites J., and Veitch, V.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs J., and Veitch, V

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:04.198623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.404746Z digest=sha256:ea5c5fcfcb17e2bec3bc76605a962169bdf695548020657534e4f5a208c469a3

Observation 02d4f182-f88c-4868-9eaa-4269cb04c415 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:04.004943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.449640Z digest=sha256:cbd96665be121fe13dd4037e802534fcc2bda21e24c6766dbff0ea46208a4692

Observation c6868f84-7684-41fa-96b3-74aaba9385cf · outbound

This paper cites Taking features out of superposition with sparse autoencoders.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Taking features out of superposition with sparse autoencoders

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:28:03.864329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.522092Z digest=sha256:15d8ead1bc68eda8817bb3ad78a23883658d3e171837c4bae1dbe3a319fdf049

Observation 6d86993c-a819-4464-a0ea-f01d9452022c · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Linear Representations of Sentiment in Large Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.642217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.642217Z digest=sha256:2ffae973fd77be4f637f22475471b4ae2ff4b92f876d9d484ba78d2693b9920a

Observation adcd7c41-c26a-4d98-b165-315dda00ac13 · outbound

This paper cites Steering Language Models With Activation Engineering.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Steering Language Models With Activation Engineering

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.713799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.713799Z digest=sha256:6d3e78da5a0177dc07b65c3f72deef9d580d6620928ad1dd7b251c190da6128d

Observation 730d33af-c380-4eea-8850-c5f8800af299 · outbound

This paper cites and Pinter, Y.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs and Pinter, Y

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.799647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.799647Z digest=sha256:5f225e721122c9c0ebf759d03a13c7008bb6a8d9abfd1f0fe9277917ee274a3d

Observation 5322eb23-947a-465a-b16b-07f53fafbde0 · outbound

This paper cites a ger, T., Elstner, J., Geisler, S., Cohen-Addad, V., G \.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs a ger, T., Elstner, J., Geisler, S., Cohen-Addad, V., G \

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T13:28:02.852685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:28:02.852685Z digest=sha256:6105c06af262c5a7a1b3585947306702893f0ed61b21548bd839b07807f409eb

Observation c854ce80-596c-465a-be17-4825780764a1 · outbound

This paper cites an unresolved cited work.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:28:03.692562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-07T13:28:02.896098Z digest=sha256:a567eda8cfb9377dcd8e27c3047f90a05c5be9f0ae9fde08fd5cb72ad0f7d0e7

Pith citing papers

Observation f5c4d94f-9caa-4c5e-8b5b-e722938ad976 · inbound

The Geometry of Harmfulness in LLMs through Subconcept Probing cites this paper.

The Geometry of Harmfulness in LLMs through Subconcept Probing From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T15:01:47.847228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T15:01:47.847228Z digest=sha256:4cda4c40ec1b878cfafdbc9fb33e556c0d7ab155571cae8f7997fec889801a5a

Observation 00337ba7-24a4-419a-acf8-a0fe04d10442 · inbound

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations cites this paper.

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-06-29T12:43:25.524172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-06-29T12:40:13.092199Z digest=sha256:d6147bfd90844053ebeba68c99b60b78f3d0c6729b747acc4e16e266439a08f4

Observation ad0b3e54-1d75-4654-8f30-753db6ba14cc · inbound

ToxiREX: A Dataset on Toxic REasoning in ConteXt cites this paper.

ToxiREX: A Dataset on Toxic REasoning in ConteXt From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

Reference 296

Resolution
verified exact
arxiv_id, observed 2026-06-29T04:43:06.981762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-06-29T04:33:18.794505Z digest=sha256:5b4ad786d39c84d05a081267e1a354706febea57357e9bb9e9337d1a8a287ac0