Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders | Paper Citation Record

Observation c5dd6416-b854-4c5a-80fe-6d72137b05a6 · inbound

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models cites this paper.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.760053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1853cc4c-7d87-4f40-9ec0-ad89cb879819 · inbound

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models cites this paper.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:29.746277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e961d9-3a53-49b2-8fec-3af767e6ca5e · inbound

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering cites this paper.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.974878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99027462-288b-4c00-9c68-0b8855948faa · inbound

Sparse Activation Editing for Reliable Instruction Following in Narratives cites this paper.

Sparse Activation Editing for Reliable Instruction Following in Narratives Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:04:54.221963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

Understanding Refusal in Language Models with Sparse Autoencoders cites this paper.

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 ee6988e0-3b75-47fa-9cb6-4de7304ae0a9 · inbound

Insights into a radiology-specialised multimodal large language model with sparse autoencoders cites this paper.

Insights into a radiology-specialised multimodal large language model with sparse autoencoders Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:42.108171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d60d8f4-3f94-4fa9-b990-187622944869 · inbound

Teach Old SAEs New Domain Tricks with Boosting cites this paper.

Teach Old SAEs New Domain Tricks with Boosting Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:28.821951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d074ad7b-8464-4353-9933-b3673759462e · inbound

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem cites this paper.

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T16:29:06.640938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6a57966-1046-450d-a424-a88a58420bd7 · inbound

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders cites this paper.

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T15:42:41.140534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc6fdef-2e70-4549-a5b4-d1e4717be92c · inbound

SATORI: Static Test Oracle Generation for REST APIs cites this paper.

SATORI: Static Test Oracle Generation for REST APIs Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:48.585241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5698882d-c7a7-4f81-98df-faad84fcd714 · inbound

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation cites this paper.

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T17:16:33.055842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0bcefc-5bed-41ad-9f0d-67f3aa10abcc · inbound

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth cites this paper.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.595697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7efdee6-ed2f-45ee-89f0-9a8a067e5e4b · inbound

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework cites this paper.

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:16:43.753837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f7debc33-1c98-417d-9279-3b3b7223897b · inbound

Towards Atoms of Large Language Models cites this paper.

Towards Atoms of Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.165968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1491b3f6-15cd-40b5-91be-a605761b234d · inbound

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 107

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T12:40:54.699308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6a47acc6-3553-492c-ac78-6c0fc4987e5a · inbound

Language Model Circuits Are Sparse in the Neuron Basis cites this paper.

Language Model Circuits Are Sparse in the Neuron Basis Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T06:35:33.800432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feddd9b1-463e-42c8-acff-10c4c15954d3 · inbound

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs cites this paper.

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 600

Resolution: unresolved; no resolver link, observed 2026-08-03T01:14:58.085415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca8806d-4c3a-4414-a648-faff8fc52a49 · inbound

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering cites this paper.

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T05:36:47.887167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01801f0c-9b33-4699-b891-51ecca4002d3 · inbound

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping cites this paper.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.765091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b2b331e2-e670-4319-a9fb-8dce35d6a686 · inbound

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

From Weights to Activations: Is Steering the Next Frontier of Adaptation? Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:55:24.615581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fc9ee04c-7102-4d90-96b3-9762fdfc9708 · inbound

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders cites this paper.

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-10T02:53:29.657509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c2306d6-a71d-435a-b291-185108bad2fb · inbound

Knowledge Vector of Logical Reasoning in Large Language Models cites this paper.

Knowledge Vector of Logical Reasoning in Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:16:32.876799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e7682740-a95d-43ff-a262-27a7b1e7cd8e · inbound

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction cites this paper.

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:00:36.281729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e323262-9627-4746-8f89-d802ab54aa8d · inbound

How Language Models Process Negation cites this paper.

How Language Models Process Negation Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:25:45.389251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1412c016-d18f-4dd4-a764-2351ea339a63 · inbound

How Language Models Process Negation cites this paper.

How Language Models Process Negation Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T00:15:09.371689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a6d8e159-28d7-437e-b541-8774363c8e87 · inbound

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

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:10:37.078332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2b9d8e00-97e1-455c-b3b2-eb8556d2584f · inbound

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

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T14:57:40.198964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 844ab031-b11e-491b-98fb-cfd37c219db2 · inbound

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features cites this paper.

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:27:58.939127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3fd20e04-d2c2-4da1-8562-72a8335a1a12 · inbound

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection cites this paper.

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:36:39.343151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 353ca87a-e502-4550-bac0-9ee30ab4cf4b · inbound

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions cites this paper.

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T15:03:31.590058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d250513c-cd86-4bf2-8496-939a085faab0 · inbound

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

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T14:23:30.743712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9a2027af-1fd8-47ee-bdfa-59c6a4b40419 · inbound

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

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.322308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b68d60-8695-47bb-bbbd-ad7bc12dd4d0 · inbound

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing cites this paper.

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T14:03:29.443692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation af4d1441-e7e8-4c56-99fd-494dd62c61f4 · inbound

How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings cites this paper.

How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:46:11.043660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 268b9d15-03fd-4494-a92f-09cb4f3094a8 · inbound

Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics cites this paper.

Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:27:25.653185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8968abbf-079b-4376-b671-7c33051b203f · inbound

Discovering Millions of Interpretable Features with Sparse Autoencoders cites this paper.

Discovering Millions of Interpretable Features with Sparse Autoencoders Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:59:53.068921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 88194d69-50b9-4d5e-b068-383929996362 · inbound

NeuroCogMap Reveals Cognitive Organization of Large Language Models cites this paper.

NeuroCogMap Reveals Cognitive Organization of Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 83

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:46:27.620414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 60b03b10-a014-49a2-907e-824206c2bffa · inbound

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control cites this paper.

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T13:23:22.708604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f720c7-61e1-47f8-a0ca-3c7110429a39 · inbound

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects cites this paper.

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T10:03:56.027290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a323459e-dba7-4de9-9f43-9d2a1f96896d · inbound

Where Steering Signals Come From: Activation Source Selection in Activation Steering cites this paper.

Where Steering Signals Come From: Activation Source Selection in Activation Steering Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T03:00:44.868666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcf4e245-00ab-4d35-9255-faf36a8d63f5 · inbound

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models cites this paper.

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:13:36.771985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers