Training LLMs to Report Their Learned Behaviors
☆31Apr 28, 2026Updated 6 months ago
Alternatives and similar repositories for introspection-adapters
Users that are interested in introspection-adapters are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆16Oct 13, 2025Updated last year
- ☆20Jun 3, 2026Updated 5 months ago
- Code for the "Mechanisms of Introspective Awareness" paper.☆48Apr 16, 2026Updated 6 months ago
- Code for Learning to Interpret Weight Differences in Language Models (Goel et al. 2025)☆22Jan 4, 2026Updated 10 months ago
- ☆37Oct 8, 2026Updated last month
- 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.
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"☆11Feb 13, 2026Updated 9 months ago
- ☆13Sep 11, 2025Updated last year
- ☆14Oct 6, 2026Updated last month
- Codebase for Temporal SAEs paper☆28Nov 14, 2025Updated 11 months ago
- ☆20Updated this week
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆183Jan 20, 2026Updated 9 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆42Jul 7, 2026Updated 4 months ago
- ☆15Dec 4, 2024Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- a bunch of rubrics I made in different format and structure for llm judge and other use cases☆16Sep 22, 2025Updated last year
- Manuscript figures and panel data for the EVEE (Evo Variant Effect Explorer) paper☆22Oct 16, 2026Updated 3 weeks ago
- Inference API for many LLMs and other useful tools for empirical research☆143May 29, 2026Updated 5 months ago
- No-chain-of-thought reasoning benchmark (NCRI): sealed banks, no-CoT runner with witnesses, frozen placement, scores for 285 models☆28Updated this week
- Train Embedding Models on MLX.☆17Jun 2, 2026Updated 5 months ago
- ☆34Nov 11, 2025Updated last year
- Code and data for the paper "LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs"☆52Oct 30, 2026Updated 2 weeks ago
- Code for Negation Neglect☆18May 22, 2026Updated 5 months ago
- Parameter Decomposition☆155Nov 6, 2026Updated last week
- 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.
- ☆16May 15, 2026Updated 5 months ago
- ☆15Sep 29, 2026Updated last month
- ☆105Sep 26, 2026Updated last month
- Auditing agents for fine-tuning safety☆22Oct 21, 2025Updated last year
- Code for "Unifying Grokking and Double Descent" from the NeurIPS 2022 ML Safety Workshop.☆11Feb 17, 2023Updated 3 years ago
- Proteus 2.0☆10Updated this week
- ☆31Jan 7, 2026Updated 10 months ago
- A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on …☆175Updated this week
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆147Oct 27, 2025Updated 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.
- When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents☆15Oct 20, 2026Updated 3 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- ☆18Jun 2, 2026Updated 5 months ago
- Generating, validating and running exploitable verifiable coding problems☆15Sep 30, 2026Updated last month
- ☆12Nov 11, 2025Updated last year
- The Elixir operating system☆23Oct 23, 2026Updated 3 weeks ago
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆36Oct 5, 2026Updated last month
Are these results useful?