Paper Citation Record · LEDGER

Investigating task-specific prompts and sparse autoencoders for activation monitoring

As of 24 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 4 inbound Pith citation observations for arXiv:2504.20271.

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

pith.paper-citation-record.v1
2504.20271 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:38:12.261958Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:33:08.616839Z

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

24 of 24 outbound references displayed

verified exact0
verified fuzzy3
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 31425d2e-627d-4bbc-9e6c-5835df5f3dfd · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.140523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36ea0f9a-3b0e-4770-a6dd-f3b9fc04c57f · outbound

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

Investigating task-specific prompts and sparse autoencoders for activation monitoring The Internal State of an LLM Knows When It's Lying

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.146195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d374e25b-a50e-46e2-85a2-5ce7f3fd72fb · outbound

This paper cites Interpretability and Analysis in Neural NLP.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Interpretability and Analysis in Neural NLP

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.151065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f4026c-9446-46dd-a2b4-da0212def674 · outbound

This paper cites Using Dictionary Learning Features as Classifiers , October 2024.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Using Dictionary Learning Features as Classifiers , October 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:38:12.849294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a2cac27f-7f58-424d-9b9e-c9fca18c416a · outbound

This paper cites Bitterman.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Bitterman

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.161369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ef6fc6c-fa34-45a6-8353-bf8ece5e5257 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Scaling and evaluating sparse autoencoders

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.167317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db1b8e8-fb36-41c4-8e55-c8f1550e3a91 · outbound

This paper cites Detecting Strategic Deception Using Linear Probes.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Detecting Strategic Deception Using Linear Probes

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.172311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b6c2c0a-b9f2-41ea-8a1e-e45c6e83d902 · outbound

This paper cites Estimating Knowledge in Large Language Models Without Generating a Single Token.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Estimating Knowledge in Large Language Models Without Generating a Single Token

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.178476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a574b75-8ac1-4083-b4d5-c7cd70aff09b · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.185035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07846e73-1896-4dea-a1a5-d4db398fdbcd · outbound

This paper cites Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.189972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b9c0478-acbb-489f-92ca-62ff44cb76bd · outbound

This paper cites Saes (usually) transfer between base and chat models.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Saes (usually) transfer between base and chat models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:38:12.832416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 19ac179a-3c89-4e98-af3d-968f075614de · outbound

This paper cites Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.199432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d21aa153-11fe-4432-8101-762d0812acad · outbound

This paper cites LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations.

Investigating task-specific prompts and sparse autoencoders for activation monitoring LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.204402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfcfbdb8-e452-4910-a45c-ff8343918472 · outbound

This paper cites LatentQA : Teaching LLMs to Decode Activations Into Natural Language , December 2024.

Investigating task-specific prompts and sparse autoencoders for activation monitoring LatentQA : Teaching LLMs to Decode Activations Into Natural Language , December 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.209001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9dc901-64a7-42dc-9256-135ecf41995f · outbound

This paper cites Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.212980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8edec60-bb15-4a56-a9b3-8dec15f0d3ac · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.217492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8883d1e-35f1-4677-b954-4cc10b0a6b76 · outbound

This paper cites Negative Results for Sparse Autoencoders On Downstream Tasks and Deprioritising SAE Research ( Mechanistic Interpretability Team Progress Update ), March 2025.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Negative Results for Sparse Autoencoders On Downstream Tasks and Deprioritising SAE Research ( Mechanistic Interpretability Team Progress Update ), March 2025

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:38:12.815384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e8b46aef-336d-470e-aab9-9053eb69ebdc · outbound

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

Investigating task-specific prompts and sparse autoencoders for activation monitoring Linear Representations of Sentiment in Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.228002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6231d726-a778-47b9-b3f3-b19517bcab23 · outbound

This paper cites Measuring short-form factuality in large language models.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Measuring short-form factuality in large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.232963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84e38454-4699-493d-a7d1-83bb5a506007 · outbound

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

Investigating task-specific prompts and sparse autoencoders for activation monitoring Representation Engineering: A Top-Down Approach to AI Transparency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.239148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59355bd8-b4ac-42b2-a5bb-5ef85bd81347 · outbound

This paper cites write newline.

Investigating task-specific prompts and sparse autoencoders for activation monitoring write newline

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.243636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2eccc7f-c781-4540-a26f-7b0446d678b8 · outbound

This paper cites @esa (Ref.

Investigating task-specific prompts and sparse autoencoders for activation monitoring @esa (Ref

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.250627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e81d7f-3d7a-4346-b0d5-6853a891ea99 · outbound

This paper cites an unresolved cited work.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.255986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ccd0b33-e751-4204-959a-29793bcf5584 · outbound

This paper cites an unresolved cited work.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:38:12.763834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 13e64531-f004-44ad-ad14-43ff8a01c0cc · inbound

The Impact of Off-Policy Training Data on Probe Generalisation cites this paper.

The Impact of Off-Policy Training Data on Probe Generalisation Investigating task-specific prompts and sparse autoencoders for activation monitoring

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-17T20:30:11.699412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98f74723-b825-4e60-bfb5-d3966bbc6ca4 · inbound

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail cites this paper.

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail Investigating task-specific prompts and sparse autoencoders for activation monitoring

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T18:33:08.616839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535510f5-cd6c-4f2a-a361-13eadb3b179d · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Investigating task-specific prompts and sparse autoencoders for activation monitoring

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:51:22.912886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3e9a3674-c821-48f4-ab11-24ebaa2ed743 · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Investigating task-specific prompts and sparse autoencoders for activation monitoring

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:07:40.529521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.