Paper Citation Record · LEDGER

Understanding Refusal in Language Models with Sparse Autoencoders

As of 22 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 9 inbound Pith citation observations for arXiv:2505.23556.

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

pith.paper-citation-record.v1
2505.23556 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:51:10.182264Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:29:10.162261Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation b87d6d4b-335f-42cc-89fa-210393a7eb9e · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:03.467398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e93ff0-36ae-4b15-a944-4cb0f21bc61e · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:03.619692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95277383-8242-4f8a-8a42-fe60862e2112 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:03.761845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211e4844-e50f-4bbe-b5b7-1874614661ca · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:11.715851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 98250a6e-29fd-4602-af8c-bc8cce841dab · outbound

This paper cites Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic.

Understanding Refusal in Language Models with Sparse Autoencoders Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.068736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60c2fc83-26ef-4266-8811-a18de25e7d80 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.194499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7893635b-1fa0-4c09-933e-b8557ff57963 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.321203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42248491-c859-41ee-acdc-6b0213e6eaa7 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Understanding Refusal in Language Models with Sparse Autoencoders JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.473685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52bbbad2-7c50-4c86-a9d3-ffbcf6aa453b · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Understanding Refusal in Language Models with Sparse Autoencoders Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.618404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db5d23af-9292-46f2-9bad-d318f9e87674 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Understanding Refusal in Language Models with Sparse Autoencoders Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.777831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720b51ec-f4e6-4112-b544-9b759b2dde22 · outbound

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

Understanding Refusal in Language Models with Sparse Autoencoders Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:04.949417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e69b653-03dd-418e-8b0a-a8a0aa043636 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:11.560309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7a98e3a8-2596-4b24-b5d7-948c75dc3e0a · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:05.247504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d838ec9d-519d-4e6e-94bb-e453389c03a9 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Understanding Refusal in Language Models with Sparse Autoencoders The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:05.461723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af44740d-c367-4cd4-bd0c-892bcb47005e · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Understanding Refusal in Language Models with Sparse Autoencoders Scaling and evaluating sparse autoencoders

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:05.689549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ce27a2-0f7e-4a85-a82d-5cf9a0b595d9 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Understanding Refusal in Language Models with Sparse Autoencoders Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:06.049313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7ede9f3-942e-4dcc-862d-13d3a3d14a42 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:06.228204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a5d4ce4-2a35-4e7e-baf5-e48bbee81ccb · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:11.386932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 992be6a2-f5d8-4e64-b887-ce83982a36a1 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:11.188031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bff34266-a1b9-4506-b254-fdf81c950ee4 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:10.937356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c2500d7e-2418-48ea-b28f-8c75f15e1b48 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:06.832925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a18718c-642b-4d93-bcfb-27f9fa7b5b9a · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Understanding Refusal in Language Models with Sparse Autoencoders Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:06.983803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 033b3d0b-835c-44c5-a1c8-01599096460c · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.151569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2af9d0-3a49-4239-b8e5-d04a00236886 · outbound

This paper cites The Llama 3 Herd of Models.

Understanding Refusal in Language Models with Sparse Autoencoders The Llama 3 Herd of Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.314336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4761377d-cdb4-496a-95a2-b73a41a33e38 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.476175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 223a07a0-86ca-477d-a6b4-eba8131902a5 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Understanding Refusal in Language Models with Sparse Autoencoders HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.596205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91ce86c1-de40-40d5-99bd-f2d73162279e · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.748855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfae3ae1-ab57-40ca-93d5-8687307d2ed6 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:07.888888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8952d920-f0c1-4d1f-ac33-4e7691c130e9 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Understanding Refusal in Language Models with Sparse Autoencoders Steering Llama 2 via Contrastive Activation Addition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.004912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96326dd-1e5d-4153-8685-ad9ca6cd69f6 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Understanding Refusal in Language Models with Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.170319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ef8e97-42b3-4272-bef4-f2062076c6e2 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:51:10.697885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation eff355b6-863d-42cd-b8c1-7f22534c5888 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.467896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c174971-d0af-4c72-ab45-36cb2ab447ed · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.580910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d9c88d-664e-4bfe-a57c-52a9129ad98c · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.750101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 226d3341-e746-4397-9379-ed5d6c85a2ba · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Understanding Refusal in Language Models with Sparse Autoencoders Gemma 2: Improving Open Language Models at a Practical Size

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:08.933972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59442013-5b2c-4967-8498-697062796c5a · outbound

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

Understanding Refusal in Language Models with Sparse Autoencoders Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.089836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4dddc2-448c-4794-a271-5074f8258c15 · outbound

This paper cites Steering Language Models With Activation Engineering.

Understanding Refusal in Language Models with Sparse Autoencoders Steering Language Models With Activation Engineering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.262929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72b1cc8-7892-4934-85c7-36669fccc64d · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.416487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d993ff3-e203-472f-8ccb-c257eaccd477 · outbound

This paper cites an unresolved cited work.

Understanding Refusal in Language Models with Sparse Autoencoders Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.641665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed9f3ccb-7d07-4760-9f1f-a91681384c04 · outbound

This paper cites LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset.

Understanding Refusal in Language Models with Sparse Autoencoders LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.791159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d33019-2df4-4d84-90e6-ff7f169775eb · outbound

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

Understanding Refusal in Language Models with Sparse Autoencoders Representation Engineering: A Top-Down Approach to AI Transparency

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:09.944567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92bebfaf-7a33-4af0-ad32-735e66115c58 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Understanding Refusal in Language Models with Sparse Autoencoders Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:10.035803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4af4d7-32f3-4d9e-bd1b-88bb15045404 · outbound

This paper cites online" 'onlinestring :=.

Understanding Refusal in Language Models with Sparse Autoencoders online" 'onlinestring :=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:10.093583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb83ecf0-07e2-45d8-82ce-7769f4c81977 · outbound

This paper cites write newline.

Understanding Refusal in Language Models with Sparse Autoencoders write newline

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T12:51:10.182264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 18905129-bc63-4288-a4c1-1fe82f33c3a1 · inbound

LLMs Encode Harmfulness and Refusal Separately cites this paper.

LLMs Encode Harmfulness and Refusal Separately Understanding Refusal in Language Models with Sparse Autoencoders

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:03:16.984373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c0f68c-05f5-45de-8f2d-d8090664d7ac · inbound

Mitigating Jailbreaks with Intent-Aware LLMs cites this paper.

Mitigating Jailbreaks with Intent-Aware LLMs Understanding Refusal in Language Models with Sparse Autoencoders

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.162261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f81b681-ec55-4df4-8846-35eb76f4d1f6 · inbound

Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs cites this paper.

Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs Understanding Refusal in Language Models with Sparse Autoencoders

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T16:51:54.950442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50fabb8e-bd0e-4261-a0c6-d006327a1a4b · inbound

Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement cites this paper.

Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement Understanding Refusal in Language Models with Sparse Autoencoders

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:15:55.709614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6e7d65de-6cd4-4979-a5a7-d826d06cf823 · inbound

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness cites this paper.

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness Understanding Refusal in Language Models with Sparse Autoencoders

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-27T03:30:26.978197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 864ec7c0-b10e-4e34-93db-6fbbb1f58b78 · inbound

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets cites this paper.

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets Understanding Refusal in Language Models with Sparse Autoencoders

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:48:32.464906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation af26780e-7f3d-4c21-b934-219782f46033 · inbound

Faithfulness to Refusal: A Causal Audit of Neuron Selectors cites this paper.

Faithfulness to Refusal: A Causal Audit of Neuron Selectors Understanding Refusal in Language Models with Sparse Autoencoders

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T15:43:53.886128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation adf1c4d8-ea18-4d7f-8102-bb6a5a62a925 · inbound

Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety cites this paper.

Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety Understanding Refusal in Language Models with Sparse Autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T14:13:53.489886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df21f8a7-b267-456d-825b-74c3c73cd698 · inbound

Do LLMs Know Their Vulnerable Scenarios? cites this paper.

Do LLMs Know Their Vulnerable Scenarios? Understanding Refusal in Language Models with Sparse Autoencoders

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T20:47:41.079651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.