Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
☆446Jun 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:
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆36Jul 31, 2025Updated last year
- ☆17Mar 30, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆253May 23, 2024Updated 2 years ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆356May 13, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆269Sep 24, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆24Jun 13, 2024Updated 2 years ago
- ☆43Jul 3, 2026Updated 2 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆153Jul 19, 2024Updated 2 years ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆192Apr 23, 2025Updated last year
- [ICLR 2025] General-purpose activation steering library☆190Sep 18, 2025Updated last year
- ☆71Jun 1, 2025Updated last year
- Training Sparse Autoencoders on Language Models☆1,540Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,900Updated this week
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆1,053Aug 16, 2024Updated 2 years ago
- [ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"☆65Nov 20, 2025Updated 10 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆675Apr 4, 2025Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆465Jan 22, 2025Updated last year
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 3 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,108Updated this week
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆464Apr 22, 2026Updated 5 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 2 years ago
- Mechanistic Interpretability Visualizations using React☆366Apr 30, 2026Updated 4 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A resource repository for representation engineering in large language models☆156Nov 14, 2024Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆70Jun 9, 2025Updated last year
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆63Jul 5, 2025Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆395Jan 23, 2025Updated last year
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 5 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆216Mar 12, 2026Updated 6 months ago
- ☆428Aug 21, 2025Updated last year
- ☆25Mar 30, 2026Updated 5 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,035Aug 14, 2024Updated 2 years 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.
- ☆83Mar 30, 2025Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆37Jul 2, 2026Updated 2 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆91May 2, 2025Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆216Jun 26, 2025Updated last year
- Universal and Transferable Attacks on Aligned Language Models☆4,800Aug 2, 2024Updated 2 years ago
- ☆153Jul 7, 2025Updated last year