andyrdt / refusal_directionLinks
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆249Updated last month
Alternatives and similar repositories for refusal_direction
Users that are interested in refusal_direction are comparing it to the libraries listed below
Sorting:
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆225Updated 10 months ago
- ☆154Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- [ICLR 2025] General-purpose activation steering library☆87Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆182Updated 5 months ago
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 8 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- ☆222Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- ☆183Updated 3 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- A resource repository for representation engineering in large language models☆129Updated 8 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆50Updated 7 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆113Updated last year
- A simple unified framework for evaluating LLMs☆235Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆187Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆30Updated last year
- Sparsify transformers with SAEs and transcoders☆595Updated last week
- AI Logging for Interpretability and Explainability🔬☆124Updated last year
- ☆107Updated 2 weeks ago
- ☆89Updated 11 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆132Updated 2 months ago