Code to enable layer-level steering in LLMs using sparse auto encoders
☆35Sep 18, 2025Updated last year
Alternatives and similar repositories for sae-steering
Users that are interested in sae-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:
- [ICLR 2025] General-purpose activation steering library☆190Sep 18, 2025Updated last year
- [ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment☆18Jun 5, 2025Updated last year
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆85Jun 20, 2026Updated 3 months ago
- Experiments with representation engineering☆14Feb 28, 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.
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- The offical code for paper "What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization"☆10Jun 23, 2024Updated 2 years ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆19Jul 6, 2026Updated 2 months ago
- [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders☆64Oct 16, 2025Updated 11 months ago
- ☆13Dec 4, 2024Updated last year
- A curated list of resources for activation engineering☆141Oct 2, 2025Updated 11 months ago
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods☆228Sep 6, 2026Updated 2 weeks ago
- [ICLR26] Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning☆21Apr 16, 2026Updated 5 months ago
- A framework for implementing equivariant DL☆10May 25, 2021Updated 5 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.
- ☆15Jan 2, 2026Updated 8 months ago
- Learning Safety Constraints for Large Language Models (ICML2025)☆35May 25, 2026Updated 3 months ago
- ☆74Jan 17, 2025Updated last year
- ☆71Jun 1, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆251May 23, 2024Updated 2 years ago
- ☆13Oct 28, 2022Updated 3 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated 11 months ago
- Training Sparse Autoencoders on Language Models☆1,538Updated this week
- ☆16Feb 24, 2022Updated 4 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.
- Optimizing diffusion for production-ready speeds☆40Jan 10, 2026Updated 8 months ago
- ☆10Jun 10, 2024Updated 2 years ago
- BPE tokenization implemented in Golang 💙☆11Oct 2, 2023Updated 2 years ago
- ☆28Jan 7, 2026Updated 8 months ago
- Lab Cookbook☆42Aug 5, 2026Updated last month
- ☆36Jun 13, 2025Updated last year
- ☆10Nov 28, 2023Updated 2 years ago
- A method for steering llms to better follow instructions☆98Jun 10, 2026Updated 3 months ago
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆126Aug 11, 2026Updated last month
- 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.
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆147Feb 24, 2025Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆107Sep 21, 2023Updated 3 years ago
- Repo for vLLM Hook, an vLLM plug-in for programming internal states of models deployed on vLLM☆161Updated this week
- ☆17Updated this week
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆14May 17, 2024Updated 2 years ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆72Aug 15, 2025Updated last year