Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
☆155Mar 9, 2024Updated 2 years ago
Alternatives and similar repositories for sleeper-agents-paper
Users that are interested in sleeper-agents-paper are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Hypercorn is an ASGI and WSGI Server based on Hyper libraries and inspired by Gunicorn.☆20Jan 12, 2026Updated 9 months ago
- ☆25Sep 5, 2024Updated 2 years ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆226Oct 5, 2026Updated last week
- ☆17Jun 17, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆27Feb 14, 2024Updated 2 years ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆119Jun 13, 2024Updated 2 years ago
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Oct 6, 2026Updated last week
- ☆22Sep 9, 2021Updated 5 years ago
- Mamba support for transformer lens☆20Sep 17, 2024Updated 2 years ago
- Supplementary materials for Claude Model Cards☆25Dec 5, 2025Updated 10 months ago
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆39Sep 25, 2023Updated 3 years ago
- ☆37Nov 16, 2025Updated 11 months ago
- Development repository for the Triton language and compiler☆26Sep 17, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆19Updated this week
- Code and example data for the paper: Rule Based Rewards for Language Model Safety☆210Jul 19, 2024Updated 2 years ago
- Algebraic value editing in pretrained language models☆72Nov 1, 2023Updated 2 years ago
- Machine Learning for Alignment Bootcamp☆87Oct 6, 2026Updated last week
- ☆291Mar 2, 2024Updated 2 years ago
- "rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, A…☆43Oct 9, 2025Updated last year
- ☆24Sep 3, 2025Updated last year
- Homebrew formulae for Anthropic tools.☆33Updated this week
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆134Mar 22, 2024Updated 2 years ago
- 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.
- Project exploring 3D volumetric rendering of NEXRAD radar data.☆13Oct 23, 2023Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated 11 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆618Aug 7, 2025Updated last year
- Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy☆60Aug 10, 2026Updated 2 months ago
- ☆58Feb 13, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- ☆24Nov 11, 2024Updated last year
- Causal Analysis of Agent Behavior for AI Safety☆22Jun 27, 2023Updated 3 years ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 8 months ago
- 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.
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- ☆298Oct 1, 2024Updated 2 years ago
- ☆96Oct 8, 2025Updated last year
- ☆56Oct 23, 2023Updated 2 years ago
- The AI that helps you achieve your goals☆11Feb 4, 2024Updated 2 years ago
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆36Mar 31, 2026Updated 6 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆107Sep 21, 2023Updated 3 years ago