dmis-lab/Monet

[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers

35
/ 100
Emerging

Monet is a type of large language model (LLM) designed to make AI behavior more understandable and controllable. It takes raw text or code as input and generates human-like text or functional code snippets as output. This allows AI researchers and ML engineers to more clearly see how the model processes information and tailor its knowledge.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer focused on developing more transparent and controllable large language models.

Not ideal if you are an end-user simply looking to apply an off-the-shelf LLM for content creation or customer service without needing to understand its internal mechanisms.

AI interpretability large language models model explainability machine learning research AI safety
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

76

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Jun 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dmis-lab/Monet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.