andyrdt / refusal_directionView external linksLinks
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆340Jun 13, 2025Updated 8 months ago
Alternatives and similar repositories for refusal_direction
Users that are interested in refusal_direction are comparing it to the libraries listed below
Sorting:
- ☆18Mar 30, 2025Updated 10 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆317May 13, 2025Updated 9 months ago
- Steering Llama 2 with Contrastive Activation Addition☆207May 23, 2024Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- ☆23Jun 13, 2024Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆173Apr 23, 2025Updated 9 months ago
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆66Jun 9, 2025Updated 8 months ago
- Sparse Autoencoder Training Library☆56May 1, 2025Updated 9 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆23Jul 26, 2024Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,073Updated this week
- ☆36Apr 30, 2024Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Mar 30, 2025Updated 10 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆811Updated this week
- ☆27Oct 6, 2024Updated last year
- A resource repository for representation engineering in large language models☆148Nov 14, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 3 months ago
- ☆207Oct 14, 2025Updated 3 months ago
- Mechanistic Interpretability Visualizations using React☆320Dec 18, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆240Dec 16, 2024Updated last year
- ☆389Aug 21, 2025Updated 5 months ago
- [ICLR 2025] General-purpose activation steering library☆141Sep 18, 2025Updated 4 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92May 2, 2025Updated 9 months ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆847Aug 16, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆567Aug 7, 2025Updated 6 months ago
- ☆47Sep 29, 2024Updated last year
- ☆116Feb 11, 2025Updated last year
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆30Nov 2, 2025Updated 3 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆377Jan 23, 2025Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆163Jun 25, 2025Updated 7 months ago
- ☆16Mar 5, 2024Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Jan 11, 2025Updated last year
- Sparsify transformers with SAEs and transcoders☆692Updated this week
- A library for efficient patching and automatic circuit discovery.☆88Dec 31, 2025Updated last month
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆106May 20, 2025Updated 8 months ago
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆569Jun 11, 2024Updated last year
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆19Aug 17, 2025Updated 5 months ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆19Dec 14, 2024Updated last year