The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarre or harmful personas. This repo contains a pipeline for generating the Assistant Axis and notebooks for monitoring and steering with it.
☆167Jan 20, 2026Updated 7 months ago
Alternatives and similar repositories for assistant-axis
Users that are interested in assistant-axis are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆461Apr 22, 2026Updated 4 months ago
- ☆96Apr 18, 2026Updated 4 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- Repository for "Training Language Models To Explain Their Own Computations"☆37Jul 7, 2026Updated last month
- Inference API for many LLMs and other useful tools for empirical research☆137May 29, 2026Updated 3 months 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.
- Training LLMs to Report Their Learned Behaviors☆29Apr 28, 2026Updated 4 months ago
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆121Aug 11, 2026Updated 3 weeks ago
- Code repo for the model organisms and convergent directions of EM papers.☆81Sep 22, 2025Updated 11 months ago
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆146Feb 8, 2026Updated 6 months ago
- ☆61Jul 4, 2025Updated last year
- ☆22Mar 3, 2026Updated 5 months ago
- bloom - evaluate any behavior immediately 🌸🌱☆1,395May 7, 2026Updated 3 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆82Updated this week
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 5 months 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.
- Unified access to Large Language Model modules using NNsight☆119Updated this week
- ☆331Jan 12, 2026Updated 7 months ago
- ☆25Mar 30, 2026Updated 5 months ago
- ☆16Nov 14, 2025Updated 9 months ago
- [COLM 2026] Official implementation for "MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Mo…☆20Apr 23, 2026Updated 4 months ago
- Code for Negation Neglect☆17May 22, 2026Updated 3 months ago
- A library for training crosscoders☆18May 28, 2025Updated last year
- Agent observability and replay tooling for AI safety & interpretability research.☆115Jun 19, 2026Updated 2 months ago
- Open-sourced evaluation suite from the Monitoring Monitorability paper☆92Aug 17, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- An alignment auditing agent capable of quickly exploring alignment hypothesis☆1,316Updated this week
- Parameter Decomposition☆140Aug 24, 2026Updated last week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated last year
- A Node.Js / Neo4J tool that translates words and relations into network graphs and shows you how it all connects.☆13Oct 24, 2019Updated 6 years ago
- Datasets used in the paper "Reward hacking behavior can generalize across tasks"☆16Aug 17, 2025Updated last year
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆142Oct 27, 2025Updated 10 months ago
- ☆2,899Updated this week
- open source interpretability platform 🧠☆1,123Updated this week
- Training Sparse Autoencoders on Language Models☆1,518Updated this week
- 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.
- ☆23Jan 30, 2026Updated 7 months ago
- ☆18Jul 9, 2025Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆213Mar 12, 2026Updated 5 months ago
- ☆115Aug 8, 2024Updated 2 years ago
- Code to generate figures of paper "When do spectral gradient updates help in deep learning?"☆16Dec 3, 2025Updated 8 months ago
- ☆157Feb 10, 2026Updated 6 months ago
- ☆1,255Updated this week