Paper Citation Record · LEDGER

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

As of 22 July 2026, this Paper Citation Record lists 100 of 293 outbound references and 15 inbound Pith citation observations for arXiv:2601.14004.

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

pith.paper-citation-record.v1
2601.14004 v4

Coverage vector

measured 100 of 293 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 115 of 115 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-22T06:31:00.163083+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T21:57:28.977088Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T05:27:39.623381Z

Reference resolution

100 of 293 outbound references displayed

verified exact46
verified fuzzy45
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch8

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0672aa96-0c88-43da-9148-9ee039aa2e51 · outbound

This paper cites Elucidating mechanisms of de- mographic bias in llms for healthcare.arXiv preprint arXiv:2502.13319.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Elucidating mechanisms of de- mographic bias in llms for healthcare.arXiv preprint arXiv:2502.13319

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.794203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f14ce2ad-728a-48f3-ae40-57bbb27c9584 · outbound

This paper cites Symbols of One-Loop Integrals From Mixed Tate Motives.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Symbols of One-Loop Integrals From Mixed Tate Motives

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T12:40:54.422564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fb788280-b010-4292-b190-77c097ee5f17 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.214050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 71f02f0c-2efb-48f1-a49e-56bb77c4408e · outbound

This paper cites Physics of Language Models: Part 1, Learning Hierarchical Language Structures.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.841133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 024d76ad-7665-40ba-bcdf-41f7215c0cbb · outbound

This paper cites an unresolved cited work.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Unresolved cited work

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.289542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 04572805-1ac4-4057-b47d-53c2646ac69b · outbound

This paper cites Systematic Outliers in Large Language Models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Systematic Outliers in Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.608787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 05e4d76b-3ecc-449a-a9af-7ae2764d9c39 · outbound

This paper cites Sparse autoencoders can capture language-specific concepts across diverse languages.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Sparse autoencoders can capture language-specific concepts across diverse languages

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.797250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2f354463-2a42-4d0b-ac68-5d2546d742b4 · outbound

This paper cites Saes are good for steering–if you select the right features.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Saes are good for steering–if you select the right features

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.728176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 350b460d-f307-4106-9a77-72a939f81653 · outbound

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Refusal in language models is mediated by a single direction

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.332730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 335abcd4-e082-4faa-bb1a-4a67ae4e20f8 · outbound

This paper cites Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213–100240.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213–100240

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.475705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5df0ad2f-f9c5-41e2-baa4-e63d74380992 · outbound

This paper cites Libbrecht.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Libbrecht

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.328876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5d89409f-fc51-40d1-bc23-ae7bdff66039 · outbound

This paper cites Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.788037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e80f3e38-c2a9-41be-b253-462876d44ee7 · outbound

This paper cites Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T02:16:46.519239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 504eb541-2def-475a-9fdc-43f029d01ae0 · outbound

This paper cites What can we actually steer? a multi-behavior study of activation control.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models What can we actually steer? a multi-behavior study of activation control

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.758539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f643abdf-37bf-4643-92a3-e221791edef7 · outbound

This paper cites Steering Large Language Model Activations in Sparse Spaces.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Steering Large Language Model Activations in Sparse Spaces

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.808987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 4339f5b7-d596-4bdb-966f-d7397c39237d · outbound

This paper cites Cocarascu, F.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Cocarascu, F

Reference 16

Resolution: malformed identifier; doi_truncated, observed 2026-05-16T12:40:54.493158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation bf7efe3c-a9e9-4ea6-944c-78b10683e7f4 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.609121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e3db4012-e2c4-4cf0-b235-2b06531caf07 · outbound

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Mechanistic Interpretability for AI Safety -- A Review

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T14:22:15.575714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0418f7c9-780b-4b3d-b488-01c2af5f0242 · outbound

This paper cites Unveiling visual perception in language models: An attention head analysis approach.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Unveiling visual perception in language models: An attention head analysis approach

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.316514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 242fe570-c192-4d99-9a5e-5c8d2ff945d0 · outbound

This paper cites Hopping too late: Exploring the limitations of large language models on multi-hop queries.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Hopping too late: Exploring the limitations of large language models on multi-hop queries

Reference 20

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.463588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2681558f-3e33-44ae-acd0-ad8211eac948 · outbound

This paper cites Open source sparse autoencoders for all residual stream layers of gpt2 small.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Open source sparse autoencoders for all residual stream layers of gpt2 small

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.318549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 800a9146-8790-46a0-87ee-c4037aaf3655 · outbound

This paper cites Quantizable transform- ers: Removing outliers by helping attention heads do nothing.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Quantizable transform- ers: Removing outliers by helping attention heads do nothing

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.314498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 28ba1fcd-ef15-4b82-bf06-28073c1c0149 · outbound

This paper cites Beyond Multiple Choice: Evaluating Steering Vectors for Summarization.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Beyond Multiple Choice: Evaluating Steering Vectors for Summarization

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.612372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fc67a028-09c9-4c24-ab15-b85ae69af7fd · outbound

This paper cites Attention approximates sparse distributed memory.Advances in Neural Information Processing Systems, 34:15301–15315.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Attention approximates sparse distributed memory.Advances in Neural Information Processing Systems, 34:15301–15315

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.307559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0c7415b8-fe14-4c32-8d08-740d999246c1 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.309758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation dfd20a62-1637-475e-8751-0ed2c31c21f8 · outbound

This paper cites Large language models share representations of latent grammatical concepts across typologically diverse languages.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Large language models share representations of latent grammatical concepts across typologically diverse languages

Reference 26

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.441919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 1fc42ea8-6cec-423a-af82-df4145ac284c · outbound

This paper cites BatchTopK Sparse Autoencoders.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models BatchTopK Sparse Autoencoders

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.800252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation c9e7c049-7579-44fb-8511-4e162f33aebd · outbound

This paper cites Locating and Mitigating Gender Bias in Large Language Models, March 2024a.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Locating and Mitigating Gender Bias in Large Language Models, March 2024a

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.384641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a0d59ee3-8a6d-47c0-ad90-bf2af8c5be53 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.722220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3f941494-1f67-4850-8c3c-10d194b89aec · outbound

This paper cites Spectral filters, dark signals, and attention sinks.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Spectral filters, dark signals, and attention sinks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.368073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f9d05a81-9b94-4da6-afb1-75407fe06a3d · outbound

This paper cites Dissecting Bias in LLMs: A Mechanistic Inter- pretability Perspective, June 2025.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Dissecting Bias in LLMs: A Mechanistic Inter- pretability Perspective, June 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.370488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 372a98ef-307e-4f5b-aee5-be7718a98a8e · outbound

This paper cites TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.743424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 53f836a7-092f-4c93-a417-e28580e21987 · outbound

This paper cites A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders , journal =.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders , journal =

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.779390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 99249f8e-a6d3-4179-9b6f-bc497b75bc68 · outbound

This paper cites A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders , journal =.

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:40:54.371554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a2b08501-3761-40af-8687-c3b2e1db3f5b · outbound

This paper cites Transferring linear features across language models with model stitching.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Transferring linear features across language models with model stitching

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.392327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 91c60308-2546-4eda-8728-d968f98374d8 · outbound

This paper cites Towards under- standing safety alignment: A mechanistic perspective from safety neurons, 2025b.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Towards under- standing safety alignment: A mechanistic perspective from safety neurons, 2025b

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.303719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 6a099f27-0d54-47ad-9044-e7d70f0c7fdc · outbound

This paper cites Identifying query-relevant neurons in large language models for long-form texts.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Identifying query-relevant neurons in large language models for long-form texts

Reference 37

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.478421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2329709a-ca6d-4580-bc0c-4ac771d70645 · outbound

This paper cites Learnable privacy neurons localization in language models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Learnable privacy neurons localization in language models

Reference 38

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.460914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a1cd1844-199a-40f9-99d0-8a6878e803e7 · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.670885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 834c8db7-8a8b-44fb-8e0f-9cf66c03dd35 · outbound

This paper cites In-context sharpness as alerts: An inner representation perspective for hallucination mitigation.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models In-context sharpness as alerts: An inner representation perspective for hallucination mitigation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.299875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 69ebec01-6283-49a2-90a3-d5d045573c9e · outbound

This paper cites From yes-men to truth-tellers: Addressing sycophancy in large language models with pinpoint tuning.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models From yes-men to truth-tellers: Addressing sycophancy in large language models with pinpoint tuning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.301728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation b8b37a46-cf81-4567-9bb4-5b5dff66a14f · outbound

This paper cites Journey to the center of the knowl- edge neurons: Discoveries of language-independent knowledge neurons and degenerate knowledge neurons.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Journey to the center of the knowl- edge neurons: Discoveries of language-independent knowledge neurons and degenerate knowledge neurons

Reference 43

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.435233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 66143978-e12c-4353-837d-db6c5861b258 · outbound

This paper cites an unresolved cited work.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Unresolved cited work

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.295780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a5e765ac-5271-4e42-a298-9bbfab366a78 · outbound

This paper cites Binary autoencoder for mechanistic interpretability of large language models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Binary autoencoder for mechanistic interpretability of large language models

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.654738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e76b0cad-90f9-4c95-b052-450945f8edb3 · outbound

This paper cites Towardefficientsparseautoencoder-guidedsteeringforimproved in-context learning in large language models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Towardefficientsparseautoencoder-guidedsteeringforimproved in-context learning in large language models

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.293914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0096938e-6cb1-4544-a8dc-e1e5aadac6a5 · outbound

This paper cites Glass, and Pengcheng He.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Glass, and Pengcheng He

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.322434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e2449ef2-9dbb-46bf-97ce-1a8ba737fc1e · outbound

This paper cites Representations as Language: An Information-Theoretic Framework for Interpretability.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Representations as Language: An Information-Theoretic Framework for Interpretability

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.659255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8affefe7-1118-4781-b13e-9eed0ff0b85b · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Towards automated circuit discovery for mechanistic interpretability

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.297867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 381b13fe-c091-4cd0-87ab-ea00d6a708be · outbound

This paper cites What you can cram into a single \ & ! \# * vector: Probing sentence embeddings for linguistic properties.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models What you can cram into a single \ & ! \# * vector: Probing sentence embeddings for linguistic properties

Reference 52

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.434246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 29cd555a-5822-4909-b319-a0c6c0744dc4 · outbound

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.681708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 895162b7-c940-4967-b775-a6c5d934d0f8 · outbound

This paper cites Can we interpret latent reasoning using current mechanistic interpretabil- ity tools?.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Can we interpret latent reasoning using current mechanistic interpretabil- ity tools?

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.324594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fda1942d-568b-43f2-b5e1-6b6df3462f30 · outbound

This paper cites Steering off Course: Reliability Challenges in Steering Language Models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Steering off Course: Reliability Challenges in Steering Language Models

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.689103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation c87873f3-0468-4c00-99bf-5df4837057c2 · outbound

This paper cites doi: 10.18653/v1/2022.acl-long.581.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models doi: 10.18653/v1/2022.acl-long.581

Reference 56

Resolution: metadata mismatch; doi, observed 2026-05-16T12:40:54.431709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ff4483d5-8410-4bc1-b79a-3da158f241a6 · outbound

This paper cites The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.694199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2aa14787-030b-4f77-a841-7889563c6333 · outbound

This paper cites Neuron based personality trait induction in large language models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Neuron based personality trait induction in large language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.277205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation dbd65c2a-12b4-44b8-aa49-c40d6d0d2068 · outbound

This paper cites an unresolved cited work.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Unresolved cited work

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.355921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ec0c7c2e-7b1b-4f8b-9af0-48d0ba391029 · outbound

This paper cites Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5

Reference 60

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.402027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 302b0a82-ce11-4f6c-9c6d-f38e450855f9 · outbound

This paper cites From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.852122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5924b097-09e9-462d-8eb5-a4d38184c206 · outbound

This paper cites Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.418934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 37bc8d4c-c7fb-4a4e-8607-4106d82d1784 · outbound

This paper cites Unveiling language competence neurons: A psycholinguistic approach to model interpretability.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Unveiling language competence neurons: A psycholinguistic approach to model interpretability

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.283129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ab34e422-cff5-4907-928a-159cfee6b5e0 · outbound

This paper cites The llama 3 herd of models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models The llama 3 herd of models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.260729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 21ec9fd3-ee4f-49dc-a081-6b568a350763 · outbound

This paper cites Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.792220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation bb64a1e1-7d1f-4aa5-9480-3b70baaa0e8f · outbound

This paper cites A mathemati- cal framework for transformer circuits.Transformer Circuits Thread.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models A mathemati- cal framework for transformer circuits.Transformer Circuits Thread

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.265134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 63c59359-e099-4ed2-a1cf-13120008844f · outbound

This paper cites Toy Models of Superposition.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Toy Models of Superposition

Reference 67

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T12:40:54.438201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 853dec4d-6688-4195-a653-41033b913f57 · outbound

This paper cites L ayer S kip: Enabling Early Exit Inference and Self-Speculative Decoding.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models L ayer S kip: Enabling Early Exit Inference and Self-Speculative Decoding

Reference 68

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.455964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 28657cde-7ca5-4740-9376-0e7dfdd84a26 · outbound

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Sequential integrated gradients: a simple but effective method for explaining language models

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.279072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2d394761-3cfe-48ca-8f23-a55c6942bde0 · outbound

This paper cites doi: 10.18653/V1/2023.FINDINGS-ACL.477.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models doi: 10.18653/V1/2023.FINDINGS-ACL.477

Reference 70

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.382085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 22ba7b67-c204-42c1-9c00-b1bacbacb0e5 · outbound

This paper cites How do language models bind entities in context? InNeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models How do language models bind entities in context? InNeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.262958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f53c37eb-ce5e-4382-a38d-c96bc8906a9a · outbound

This paper cites A Primer on the Inner Workings of Transformer-based Language Models.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models A Primer on the Inner Workings of Transformer-based Language Models

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:40:54.748973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8f7b7858-ae9e-448d-8bb2-9a307e70af88 · outbound

This paper cites Truthful or fabricated? using causal attribution to mitigate reward hacking in explanations.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Truthful or fabricated? using causal attribution to mitigate reward hacking in explanations

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.254252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0c099ec6-1b8d-4e5a-9e3a-f36599310aae · outbound

This paper cites Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:05.058075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 4d41ea08-5f9b-4f65-9175-1cd9316131de · outbound

This paper cites Towards empirical in- terpretation of internal circuits and properties in grokked transformers on modular polynomials.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Towards empirical in- terpretation of internal circuits and properties in grokked transformers on modular polynomials

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.269639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 21391415-eafd-450f-be88-ba4f326f41e9 · outbound

This paper cites I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.776198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 767cbfe6-7346-4841-9bb3-15e4df135b01 · outbound

This paper cites Exploring mechanistic interpretability in large language models: Challenges, approaches, and insights.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Exploring mechanistic interpretability in large language models: Challenges, approaches, and insights

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.364064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 613023b2-0332-4556-abf4-32e099bf75ae · outbound

This paper cites H-neurons: On the existence, impact, and origin of hallucination-associated neurons in llms, 2025a.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models H-neurons: On the existence, impact, and origin of hallucination-associated neurons in llms, 2025a

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.751842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a1cee848-2c73-4a80-966d-55c29f412b01 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Scaling and evaluating sparse autoencoders

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.764524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation df0237b3-4bba-4170-b871-54d19243dbd3 · outbound

This paper cites arXiv preprint arXiv:2511.13653 , year =.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models arXiv preprint arXiv:2511.13653 , year =

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.734453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f15120e8-67ea-48cf-9aeb-e5471e5ab46f · outbound

This paper cites Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83): 1–64.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83): 1–64

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.240093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 276e03b2-7e04-4798-9558-106cf3705411 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Transformer feed-forward layers are key-value memories

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.231918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation aed21c0f-0ec6-43ae-8a92-d60d3acb0c75 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Transformer Feed-Forward Layers Are Key-Value Memories

Reference 83

Resolution: metadata mismatch; doi, observed 2026-05-16T12:40:54.465938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5a5661d1-8ecf-4426-b94d-51cce1626c26 · outbound

This paper cites Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.207204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e1aa706f-f292-4c8a-9362-fe302f782b30 · outbound

This paper cites Dissecting.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Dissecting

Reference 85

Resolution: metadata mismatch; doi, observed 2026-05-16T12:40:54.490914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5d28194c-ee2d-4f58-b964-8b7718b3c119 · outbound

This paper cites Lepori, and Lucas Dixon.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Lepori, and Lucas Dixon

Reference 86

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.429361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation d90cc237-7913-4e1c-b673-bf7524a82bb1 · outbound

This paper cites Efficient training of sparse autoencoders for large language models via layer groups.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Efficient training of sparse autoencoders for large language models via layer groups

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.685616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 61dcf6bb-62cd-4267-b15f-76211035cd59 · outbound

This paper cites Localizing Model Behavior with Path Patching.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Localizing Model Behavior with Path Patching

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-05-16T19:38:37.891054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 934145fe-623f-4d38-8f92-e2100624f98a · outbound

This paper cites Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.305390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5bc70be2-ee54-4221-9703-32f00af853c5 · outbound

This paper cites Executive control emerging from dynamic interactions between brain systems mediating language, working memory and attentional processes.Acta psychologica, 115(2-3):105–121.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Executive control emerging from dynamic interactions between brain systems mediating language, working memory and attentional processes.Acta psychologica, 115(2-3):105–121

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.251518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 774a30eb-1798-4769-88d8-75549f940c61 · outbound

This paper cites Springer.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Springer

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.253352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8ffc0ded-9f7c-487d-9a4b-f374f6efbe6d · outbound

This paper cites MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion, July 2025.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion, July 2025

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.269342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 97b81712-b155-4995-b81a-ac97c727c6ce · outbound

This paper cites Attention score is not all you need for token importance indicator in KV cache reduction: Value also matters.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Attention score is not all you need for token importance indicator in KV cache reduction: Value also matters

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.263684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 4ac3630f-4119-4b61-b32c-7aca182d061c · outbound

This paper cites doi: 10.18653/v1/2024.emnlp-main.1178.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models doi: 10.18653/v1/2024.emnlp-main.1178

Reference 95

Resolution: verified exact; doi, observed 2026-05-16T12:40:54.341029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 89e1260c-d73b-43b5-be0e-a84974de6c3f · outbound

This paper cites Enhancing Automated Interpretability with Output-Centric Feature Descriptions.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.644671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a0968755-b832-452d-ab3f-81cb198ef015 · outbound

This paper cites Language arithmetics: Towards systematic language neuron identification and manipulation, 2025a.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Language arithmetics: Towards systematic language neuron identification and manipulation, 2025a

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.678948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fa410992-5c92-4e0d-a675-2bbb5b4451f9 · outbound

This paper cites Sparse subnetwork enhancement for underrepresented languages in large language models, 2025b.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Sparse subnetwork enhancement for underrepresented languages in large language models, 2025b

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.687163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation d7c46cd2-1dab-4bc4-b9e8-c0eb03c7be8e · outbound

This paper cites Position-aware automatic circuit discovery.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Position-aware automatic circuit discovery

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.307219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a0dd5fc3-f7b4-4594-8d37-1208735d6ef5 · outbound

This paper cites Personality as a probe for LLM evaluation: Method trade-offs and downstream effects.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Personality as a probe for LLM evaluation: Method trade-offs and downstream effects

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.173531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3683568c-69a2-4534-b437-d5fd8b16c0c8 · outbound

This paper cites How does GPT-2 compute greater- than?: Interpreting mathematical abilities in a pre-trained language model.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models How does GPT-2 compute greater- than?: Interpreting mathematical abilities in a pre-trained language model

Reference 101

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.291833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 64bba6bb-41fa-4607-a5a6-196605aeaacf · outbound

This paper cites Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms

Reference 102

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.177323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3707dda1-8e1f-45ae-a0a2-05f09f74656f · outbound

This paper cites Circuit-tracer: A new library for finding feature circuits.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Circuit-tracer: A new library for finding feature circuits

Reference 103

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.287076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e91c411a-0f95-4893-85e6-801ec1eaa9e2 · outbound

This paper cites Zipcache: Accurate and efficient kv cache quantization with salient token identification.Advances in Neural Information Processing Systems, 37:68287–68307, 2024a.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Zipcache: Accurate and efficient kv cache quantization with salient token identification.Advances in Neural Information Processing Systems, 37:68287–68307, 2024a

Reference 105

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T12:40:55.177624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Pith citing papers

Observation db7c344a-33ed-4e21-bf4a-efeaf9d8d115 · inbound

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining cites this paper.

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:00:40.730979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5859c0dc-d0a2-43a5-a65c-6d7cfd8820b9 · inbound

Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality cites this paper.

Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-11T00:50:50.375821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation b8481f70-56b4-4759-a618-a19ecdabd51a · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:05:58.188305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5471908f-73fc-4b92-b61f-7e658dbf550f · inbound

From Attribution to Action: A Human-Centered Application of Activation Steering cites this paper.

From Attribution to Action: A Human-Centered Application of Activation Steering Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-11T11:21:04.815363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3fa89818-a76b-4b96-8a13-a499532f9b62 · inbound

From Attribution to Action: A Human-Centered Application of Activation Steering cites this paper.

From Attribution to Action: A Human-Centered Application of Activation Steering Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-12T21:57:28.977088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94eddccc-b65a-4bdb-9983-caa8ab68973b · inbound

The Cylindrical Representation Hypothesis for Language Model Steering cites this paper.

The Cylindrical Representation Hypothesis for Language Model Steering Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-01T00:15:09.220362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8505f45a-61d9-42c2-911a-6298a4bb58de · inbound

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training cites this paper.

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T19:56:07.741092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 739a65f5-220d-4d32-b357-d1557badf70a · inbound

Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training cites this paper.

Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T02:42:08.382307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 9190af20-379f-4fe8-a19a-6288460b472a · inbound

Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training cites this paper.

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T06:45:26.246766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 6f144e3e-a45a-427b-b8d9-9b3bd26e0b77 · inbound

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models cites this paper.

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T05:42:21.092333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7d4959ab-dc1e-4bff-b233-1d56600a080d · inbound

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond cites this paper.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 77

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.575931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ecd68893-32be-464c-9ce4-2f0d99d60289 · inbound

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning cites this paper.

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:46:10.223820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e9fda900-ecda-4f1b-ada9-2b811b5cd39e · 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 Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 121

Resolution: verified exact; local_arxiv, observed 2026-07-01T14:05:47.042635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 1df6662f-2293-49e3-8999-1b969d70c1be · 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 Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 121

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 b7ef4b74-8caa-47b0-89ab-70c3e3e99175 · inbound

READER: Robust Evidence-based Authorship Decoding via Extracted Representations cites this paper.

READER: Robust Evidence-based Authorship Decoding via Extracted Representations Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-03T05:27:39.624645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.