Cover Image

Automatically Interpreting Millions of Features in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Paulo, Gonçalo, Mallen, Alex, Juang, Caden, Belrose, Nora
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Partially Rewriting a Transformer in Natural Language
by: Paulo, Gonçalo, et al.
Published: (2025)

Does Transformer Interpretability Transfer to RNNs?
by: Paulo, Gonçalo, et al.
Published: (2024)

Eliciting Latent Knowledge from Quirky Language Models
by: Mallen, Alex, et al.
Published: (2023)

Balancing Label Quantity and Quality for Scalable Elicitation
by: Mallen, Alex, et al.
Published: (2024)

Sparse Autoencoders Trained on the Same Data Learn Different Features
by: Paulo, Gonçalo, et al.
Published: (2025)

Transcoders Beat Sparse Autoencoders for Interpretability
by: Paulo, Gonçalo, et al.
Published: (2025)

Evaluating SAE interpretability without explanations
by: Paulo, Gonçalo, et al.
Published: (2025)

Mechanistic Anomaly Detection for "Quirky" Language Models
by: Johnston, David O., et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

Refusal in LLMs is an Affine Function
by: Marshall, Thomas, et al.
Published: (2024)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

Neural Networks Learn Statistics of Increasing Complexity
by: Belrose, Nora, et al.
Published: (2024)

Slowing Learning by Erasing Simple Features
by: Quirke, Lucia, et al.
Published: (2025)

Automatic Prompt Selection for Large Language Models
by: Do, Viet-Tung, et al.
Published: (2024)

LEACE: Perfect linear concept erasure in closed form
by: Belrose, Nora, et al.
Published: (2023)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
by: Soo, Samuel, et al.
Published: (2025)

Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
by: Faria, Gonçalo, et al.
Published: (2025)

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
by: Laptev, Daniil, et al.
Published: (2025)

Crafting Large Language Models for Enhanced Interpretability
by: Sun, Chung-En, et al.
Published: (2024)

Binary Sparse Coding for Interpretability
by: Quirke, Lucia, et al.
Published: (2025)

Investigating Automatic Scoring and Feedback using Large Language Models
by: Katuka, Gloria Ashiya, et al.
Published: (2024)

A Review of Developmental Interpretability in Large Language Models
by: Kendiukhov, Ihor
Published: (2025)

Rotary Offset Features in Large Language Models
by: Jonasson, André
Published: (2025)

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
by: Lab, Mind, et al.
Published: (2026)

Semantic Structure of Feature Space in Large Language Models
by: Kozlowski, Austin C., et al.
Published: (2026)

Persistent Topological Features in Large Language Models
by: Gardinazzi, Yuri, et al.
Published: (2024)

How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective
by: Peng, Runyu, et al.
Published: (2026)

Latent Feature Mining for Predictive Model Enhancement with Large Language Models
by: Li, Bingxuan, et al.
Published: (2024)

Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation
by: Jacobi, Jonathan, et al.
Published: (2025)

Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
by: He, Zhengfu, et al.
Published: (2024)

Rethinking Interpretability in the Era of Large Language Models
by: Singh, Chandan, et al.
Published: (2024)

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
by: Clymer, Joshua, et al.
Published: (2024)

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
by: Lee, Heejun, et al.
Published: (2025)

Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
by: Yang, Junjie, et al.
Published: (2025)

Capability-Guided Compression: Toward Interpretability-Aware Budget Allocation for Large Language Models
by: Gupta, Rishaank
Published: (2026)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
by: Cho, Hakaze, et al.
Published: (2025)

Pre-trained Large Language Models Use Fourier Features to Compute Addition
by: Zhou, Tianyi, et al.
Published: (2024)

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
by: Deng, Boyi, et al.
Published: (2026)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling
by: Egli, Eric, et al.
Published: (2025)