Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆413Jun 13, 2025Updated last year
Alternatives and similar repositories for refusal_direction
Users that are interested in refusal_direction are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Mar 30, 2025Updated last year
- ☆25Jun 13, 2024Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆239May 23, 2024Updated 2 years ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆340May 13, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆264Sep 24, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆154Jul 19, 2024Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆68Jun 9, 2025Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆184Apr 23, 2025Updated last year
- Training Sparse Autoencoders on Language Models☆1,442Jun 24, 2026Updated last week
- A resource repository for representation engineering in large language models☆155Nov 14, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,603Jun 27, 2026Updated last week
- ☆425Aug 21, 2025Updated 10 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆90Mar 30, 2025Updated last year
- Mechanistic Interpretability Visualizations using React☆353Apr 30, 2026Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆262Updated this week
- Sparse Autoencoder Training Library☆57May 1, 2025Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆388Jan 23, 2025Updated last year
- [ICLR 2025] General-purpose activation steering library☆178Sep 18, 2025Updated 9 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 8 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Jan 11, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆971Jun 29, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆997Aug 16, 2024Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆108May 20, 2025Updated last year
- ☆33Jun 24, 2024Updated 2 years ago
- ☆38Apr 30, 2024Updated 2 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆90May 2, 2025Updated last year
- ☆219Oct 14, 2025Updated 8 months ago
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆664Jun 11, 2024Updated 2 years ago
- ☆213Nov 17, 2024Updated last year
- ☆27Oct 6, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆201Nov 26, 2023Updated 2 years ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆176Dec 18, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆598Aug 7, 2025Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆262Feb 27, 2026Updated 4 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆22Jun 12, 2026Updated 3 weeks ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆96May 9, 2025Updated last year