Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆365Jun 13, 2025Updated 9 months ago
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 11 months ago
- ☆23Jun 13, 2024Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆220May 23, 2024Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆322May 13, 2025Updated 10 months ago
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆152Jul 19, 2024Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆67Jun 9, 2025Updated 9 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆176Apr 23, 2025Updated 11 months ago
- Training Sparse Autoencoders on Language Models☆1,272Mar 19, 2026Updated last week
- A library for mechanistic interpretability of GPT-style language models☆3,223Updated this week
- A resource repository for representation engineering in large language models☆149Nov 14, 2024Updated last year
- ☆403Aug 21, 2025Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆246Updated this week
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Mechanistic Interpretability Visualizations using React☆332Dec 18, 2024Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Mar 30, 2025Updated 11 months ago
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- 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
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Jan 11, 2025Updated last year
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 4 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆871Updated this week
- ☆36Apr 30, 2024Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆107May 20, 2025Updated 10 months ago
- NordVPN Special Discount Offer • AdSave on top-rated NordVPN 1 or 2-year plans with secure browsing, privacy protection, and support for for all major platforms.
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆879Aug 16, 2024Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92May 2, 2025Updated 10 months ago
- ☆211Oct 14, 2025Updated 5 months ago
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆606Jun 11, 2024Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆380Jan 23, 2025Updated last year
- [ICLR 2025] General-purpose activation steering library☆153Sep 18, 2025Updated 6 months ago
- ☆199Nov 17, 2024Updated last year
- ☆27Oct 6, 2024Updated last year
- ☆33Feb 15, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆88May 9, 2025Updated 10 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆57Sep 22, 2025Updated 6 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆576Aug 7, 2025Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated last month
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆21Mar 20, 2025Updated last year
- Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024☆18Mar 25, 2025Updated last year