[ICLR 2025] General-purpose activation steering library
☆195Oct 23, 2026Updated last week
Alternatives and similar repositories for activation-steering
Users that are interested in activation-steering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Steering Llama 2 with Contrastive Activation Addition☆260May 23, 2024Updated 2 years ago
- A resource repository for representation engineering in large language models☆161Nov 14, 2024Updated last year
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆36Sep 18, 2025Updated last year
- [ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"☆69Nov 20, 2025Updated 11 months ago
- 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.
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆474Jun 13, 2025Updated last year
- [EMNLP 2026] A Unified Framework for High-Performance and Extensible LLM Steering☆312Updated this week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- An exploration of LLM steering☆29Jun 15, 2024Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆165Feb 21, 2025Updated last year
- ☆19Sep 1, 2025Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆51Jul 28, 2024Updated 2 years ago
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆31Jan 29, 2026Updated 9 months ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆23Dec 14, 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. Zero configuration with optimized deployments.
- A curated list of resources for activation engineering☆140Oct 2, 2025Updated last year
- ☆14Feb 11, 2025Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆218Mar 12, 2026Updated 7 months ago
- A method for steering llms to better follow instructions☆99Jun 10, 2026Updated 4 months ago
- ☆13Jun 5, 2024Updated 2 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆914Mar 6, 2026Updated 7 months ago
- ☆14Jan 2, 2026Updated 9 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆14Jan 26, 2025Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 2024Updated 2 years ago
- 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.
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,054Aug 14, 2024Updated 2 years ago
- A library for mechanistic interpretability of GPT-style language models☆4,019Updated this week
- Official code repository for the paper "Internal Activation as the Polar Star for Steering Unsafe LLM Behavior"☆16May 31, 2026Updated 5 months ago
- Official implementation repository for the paper Towards General Conceptual Model Editing via Adversarial Representation Engineering.☆20Dec 6, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,577Oct 20, 2026Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆277Feb 27, 2026Updated 8 months ago
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- ☆71Jun 1, 2025Updated last year
- Internalizing steering vectors via fine tuning☆12Sep 6, 2024Updated 2 years ago
- 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.
- ☆301Oct 1, 2024Updated 2 years ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆88Jun 20, 2026Updated 4 months ago
- How do transformer LMs encode relations?☆59Feb 24, 2024Updated 2 years ago
- Algebraic value editing in pretrained language models☆73Nov 1, 2023Updated 2 years ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆65Jul 5, 2025Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆587Jan 28, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,137Updated this week