Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆370Jun 13, 2025Updated 10 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 last year
- ☆23Jun 13, 2024Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆222May 23, 2024Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆324May 13, 2025Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆260Sep 24, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 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
- 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
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆66Jun 9, 2025Updated 10 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆178Apr 23, 2025Updated 11 months ago
- Training Sparse Autoencoders on Language Models☆1,312Mar 19, 2026Updated 3 weeks ago
- A library for mechanistic interpretability of GPT-style language models☆3,304Updated this week
- A resource repository for representation engineering in large language models☆150Nov 14, 2024Updated last year
- ☆408Aug 21, 2025Updated 7 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.
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆250Updated this week
- Mechanistic Interpretability Visualizations using React☆338Dec 18, 2024Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Mar 30, 2025Updated last year
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 11 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆381Jan 23, 2025Updated last year
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 5 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.☆893Updated this week
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆915Aug 16, 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.
- ☆37Apr 30, 2024Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆108May 20, 2025Updated 10 months ago
- ☆33Jun 24, 2024Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆90May 2, 2025Updated 11 months ago
- ☆212Oct 14, 2025Updated 6 months ago
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆624Jun 11, 2024Updated last year
- [ICLR 2025] General-purpose activation steering library☆160Sep 18, 2025Updated 6 months ago
- ☆204Nov 17, 2024Updated last year
- ☆198Nov 26, 2023Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆27Oct 6, 2024Updated last year
- ☆34Feb 15, 2026Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆104Sep 21, 2023Updated 2 years ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆175Dec 18, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆254Feb 27, 2026Updated last month
- Tools for understanding how transformer predictions are built layer-by-layer☆584Aug 7, 2025Updated 8 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆22Mar 20, 2025Updated last year