Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
☆222Jul 17, 2026Updated this week
Alternatives and similar repositories for Llamascopium
Users that are interested in Llamascopium are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Training Sparse Autoencoders on Language Models☆1,476Updated this week
- ☆177May 1, 2026Updated 2 months ago
- ☆30Nov 9, 2025Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆732Updated this week
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years 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.
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 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 …☆266Jul 13, 2026Updated last week
- ☆26Aug 23, 2025Updated 10 months ago
- ☆427Aug 21, 2025Updated 11 months ago
- ☆109May 23, 2026Updated last month
- Applying SAEs for fine-grained control☆27Dec 15, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆28Nov 20, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆265Feb 27, 2026Updated 4 months ago
- ☆223Oct 14, 2025Updated 9 months ago
- 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.
- Sparse Autoencoder for Mechanistic Interpretability☆303Jul 20, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,695Updated this week
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 5 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆995Updated this week
- ☆16Nov 14, 2025Updated 8 months ago
- ☆60Nov 19, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆306Nov 10, 2023Updated 2 years ago
- ☆595Jul 19, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- ☆212Nov 17, 2024Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆34Sep 18, 2025Updated 10 months ago
- ☆78Mar 6, 2025Updated last year
- OpenMOSS presents a collection of our research on LLMs, supported by SII, Fudan and Mosi.☆30Updated this week
- [ICML'2024] Can AI Assistants Know What They Don't Know?☆86Feb 5, 2024Updated 2 years ago
- A quick way to get started with Transformer Lens☆14Dec 13, 2023Updated 2 years ago
- ☆113Aug 8, 2024Updated last year
- awesome SAE papers☆78May 24, 2025Updated last year
- 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.
- Modified to support crosscoder training.☆27Jul 2, 2026Updated 2 weeks ago
- ☆293Oct 1, 2024Updated last year
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆15May 25, 2026Updated last month
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆13Jan 26, 2025Updated last year
- Mechanistic Interpretability Visualizations using React☆358Apr 30, 2026Updated 2 months ago
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- ☆17Feb 14, 2024Updated 2 years ago