redwoodresearch / alignment_faking_publicView external linksLinks
☆83Oct 8, 2025Updated 4 months ago
Alternatives and similar repositories for alignment_faking_public
Users that are interested in alignment_faking_public are comparing it to the libraries listed below
Sorting:
- ☆22Sep 9, 2021Updated 4 years ago
- ☆10Feb 25, 2020Updated 5 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆127Mar 9, 2024Updated last year
- ☆20Nov 15, 2024Updated last year
- Sparse Autoencoder Training Library☆56May 1, 2025Updated 9 months ago
- A quick way to get started with Transformer Lens☆14Dec 13, 2023Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 3 months ago
- Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge☆14Feb 20, 2024Updated last year
- Interpreting Learned Search and Planning: Reverse-engineering recurrent convolutional networks (DRC) that play Sokoban☆17Jun 29, 2025Updated 7 months ago
- ☆14Oct 7, 2022Updated 3 years ago
- Measuring the situational awareness of language models☆40Feb 12, 2024Updated 2 years ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆52Apr 6, 2025Updated 10 months ago
- Situational Awareness Dataset☆43Dec 14, 2024Updated last year
- A TinyStories LM with SAEs and transcoders☆14Apr 3, 2025Updated 10 months ago
- Repository with sample code using Apollo's suggested engineering practices☆15Dec 16, 2024Updated last year
- Automatically create Anki cards from text using language models☆20Jan 7, 2023Updated 3 years ago
- ☆36Apr 30, 2024Updated last year
- ☆17Updated this week
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆16Sep 15, 2023Updated 2 years ago
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- Einsum with einops style variable names☆18May 16, 2024Updated last year
- This git repository outlines three scoring rules that I believe might serve current forecasting platforms better than current alternative…☆18Apr 18, 2022Updated 3 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆567Aug 7, 2025Updated 6 months ago
- (Model-written) LLM evals library☆18Dec 13, 2024Updated last year
- A formalisation of Cartesian Frames, a perspective on embedded agency, in the HOL theorem prover.☆20Dec 20, 2021Updated 4 years ago
- ☆24Aug 7, 2025Updated 6 months ago
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆27Apr 2, 2025Updated 10 months ago
- ☆21Nov 11, 2024Updated last year
- A gym environment for Stuart Armstrong's model of a treacherous turn.☆18Jul 28, 2018Updated 7 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆153Updated this week
- Author's PyTorch implementation of SR-DICE for marginalized importance sampling☆28Dec 7, 2021Updated 4 years ago
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Jan 26, 2024Updated 2 years ago
- Code for Continual Reinforcement Learning with Multi-Timescale Replay☆24Apr 16, 2020Updated 5 years ago
- ☆58Nov 19, 2024Updated last year
- ☆27Oct 6, 2024Updated last year
- ☆60Mar 9, 2023Updated 2 years ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆124Mar 22, 2024Updated last year
- MCP server for Oura API integration☆37Feb 27, 2025Updated 11 months ago