Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
☆38Jul 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:
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆472Jun 13, 2025Updated last year
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆49Oct 13, 2025Updated last year
- ☆19Nov 5, 2025Updated 11 months ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- ☆22Oct 25, 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.
- ☆71Jun 1, 2025Updated last year
- SAEs in Jax☆12Dec 16, 2024Updated last year
- An agent-first design tool for the .pen format, enabling export to SwiftUI and React☆10Updated this week
- Improving Alignment and Robustness with Circuit Breakers☆271Sep 24, 2024Updated 2 years ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 4 months ago
- Fingerprint large language models☆52Jul 11, 2024Updated 2 years ago
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆31Jan 29, 2026Updated 9 months 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
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- EMNLP 25 Oral - AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender☆20Feb 7, 2026Updated 8 months ago
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆30Oct 23, 2025Updated last year
- ☆12Jun 30, 2024Updated 2 years ago
- ☆160Jul 7, 2025Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆467Jan 22, 2025Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆75Oct 23, 2024Updated 2 years 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
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 4 months ago
- Toolbox to run adversarial attacks against LLM.☆39Aug 31, 2026Updated last month
- 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.
- [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
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆71Jun 9, 2025Updated last year
- The opensoure repository of FuzzLLM☆37May 4, 2024Updated 2 years ago
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- Code for Chain-of-Thought Hijacking☆30Nov 10, 2025Updated 11 months ago
- ☆62Mar 9, 2023Updated 3 years ago
- [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
- ☆47Jul 3, 2026Updated 3 months ago
- FLECC_IN_C is a FLexible Elliptic Curve Cryptography library written IN C☆18Nov 17, 2017Updated 8 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆1,083Aug 16, 2024Updated 2 years ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆38Jul 2, 2026Updated 3 months ago
- This repository contains code for the paper "Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Lang…☆10Nov 12, 2024Updated last year
- ☆25Jun 10, 2025Updated last year
- [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆182Aug 11, 2026Updated 2 months ago
- https://scale.com/research/mrt☆21Mar 16, 2026Updated 7 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year