anthropics / sleeper-agents-paperView external linksLinks
Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
☆127Mar 9, 2024Updated last year
Alternatives and similar repositories for sleeper-agents-paper
Users that are interested in sleeper-agents-paper are comparing it to the libraries listed below
Sorting:
- ☆25Sep 5, 2024Updated last year
- ☆17Updated this week
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Jun 13, 2024Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Jan 26, 2026Updated 2 weeks ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆13Feb 13, 2023Updated 3 years ago
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 3 months ago
- Sparse Autoencoder Training Library☆56May 1, 2025Updated 9 months ago
- ☆12Oct 23, 2022Updated 3 years ago
- ☆284Mar 2, 2024Updated last year
- Display and customize Markdown text in SwiftUI☆33Jan 28, 2025Updated last year
- CS194-196 Course Project☆14Feb 20, 2025Updated 11 months ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Apr 18, 2024Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆124Mar 22, 2024Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- Algebraic value editing in pretrained language models☆68Nov 1, 2023Updated 2 years ago
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆27Mar 1, 2025Updated 11 months ago
- ☆52Feb 13, 2024Updated 2 years ago
- ☆83Oct 8, 2025Updated 4 months ago
- ☆17Sep 4, 2024Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆58Feb 12, 2024Updated 2 years ago
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆36Sep 25, 2023Updated 2 years ago
- A formalisation of Cartesian Frames, a perspective on embedded agency, in the HOL theorem prover.☆20Dec 20, 2021Updated 4 years ago
- gpt completions in vscode☆35Mar 24, 2023Updated 2 years ago
- ☆21Nov 11, 2024Updated last year
- Project exploring 3D volumetric rendering of NEXRAD radar data.☆11Oct 23, 2023Updated 2 years ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆66Apr 24, 2024Updated last year
- Erasing concepts from neural representations with provable guarantees☆243Jan 27, 2025Updated last year
- ☆51Oct 23, 2023Updated 2 years ago
- ☆23Apr 23, 2024Updated last year
- ☆27Apr 11, 2023Updated 2 years ago
- Code and example data for the paper: Rule Based Rewards for Language Model Safety☆205Jul 19, 2024Updated last year
- ☆267Oct 1, 2024Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated this week
- ☆146Jul 23, 2025Updated 6 months ago
- (NeurIPS '22) LISA: Learning Interpretable Skill Abstractions - A framework for unsupervised skill learning using Imitation☆29Feb 22, 2023Updated 2 years ago
- ☆29Jul 17, 2023Updated 2 years ago
- ☆567Jul 19, 2024Updated last year
- ✒️ A gallery of experiments with Scalable Vector Graphics (SVG) and interactive visualizations.☆13Jan 6, 2023Updated 3 years ago