Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
☆39Jul 31, 2025Updated last year
Alternatives and similar repositories for geometry-of-refusal
Users that are interested in geometry-of-refusal are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP2025 Findings] Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction☆11Apr 9, 2026Updated 7 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆492Jun 13, 2025Updated last year
- ☆38Mar 24, 2026Updated 7 months ago
- [ICML 2026] Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control☆13Jul 12, 2026Updated 4 months ago
- [ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"☆69Nov 20, 2025Updated 11 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆48Oct 13, 2025Updated last year
- ☆19Nov 5, 2025Updated last year
- ☆71Jun 1, 2025Updated last year
- ☆48Jul 3, 2026Updated 4 months ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- ☆21Oct 25, 2024Updated 2 years ago
- Implementation of the certificates proposed in the paper "Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized …☆37Jun 27, 2023Updated 3 years ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 5 months ago
- Improving Alignment and Robustness with Circuit Breakers☆271Sep 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.
- An agent-first design tool for the .pen format, enabling export to SwiftUI and React☆12Oct 28, 2026Updated 3 weeks ago
- This project proposed a method to defense against adversarial attack. By combining the proposed preprocessing method with an adversariall…☆10Oct 4, 2018Updated 8 years ago
- code for 'Do Sparse Autoencoders Capture Concept Manifolds?'☆29May 21, 2026Updated 5 months ago
- Certifiable Robustness to Graph Perturbations☆14May 8, 2020Updated 6 years ago
- EMNLP 25 Oral - AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender☆20Feb 7, 2026Updated 9 months ago
- Generating Synthetic Lifelong RL Data for LLMs at Scale☆14Jul 9, 2026Updated 4 months ago
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆30Oct 23, 2025Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆471Jan 22, 2025Updated last year
- ☆162Jul 7, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 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
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆75Oct 23, 2024Updated 2 years ago
- [EMNLP 2025] The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Com…☆40Nov 24, 2025Updated 11 months ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- Generative Modeling with Bayesian Sample Inference☆26Aug 14, 2026Updated 3 months ago
- [MM'25] JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering☆26Dec 23, 2025Updated 10 months ago
- Toolbox to run adversarial attacks against LLM.☆39Aug 31, 2026Updated 2 months ago
- The opensoure repository of FuzzLLM☆38May 4, 2024Updated 2 years ago
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated 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.
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆71Jun 9, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 4 months ago
- Code for Chain-of-Thought Hijacking☆30Nov 10, 2025Updated last year
- volumetric brush implementation, heavily inspired by toxiclibs☆14Dec 10, 2022Updated 3 years ago
- ☆61Mar 9, 2023Updated 3 years ago
- Adversarial Manipulation of CoT☆10Nov 5, 2026Updated last week
- [NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li☆21Jun 11, 2022Updated 4 years ago
Are these results useful?