Downloads · 30 days
0
sarvam-30b-sae
Aquinlabs/sarvam-30b-sae
sarvam-30b-sae is a machine learning model from Aquinlabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for aquin. The card lists the license as apache-2.0.
Sparse autoencoder for residual-stream features of sarvamai/sarvam-30b.
Access
Public
Updated Jul 19, 2026
Repo size
1.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt1.1 GB · 100%
At a glance
- Library
- aquin
- License
- apache-2.0
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026
- SHA
- f8dc91af
Base models
Model card
From the Hugging Face model README
Sarvam-30B SAE (Layer 9)
Sparse autoencoder for residual-stream features of sarvamai/sarvam-30b.
Specs
| Field | Value |
|---|---|
| Base model | sarvamai/sarvam-30b |
| Hook | hook_resid_post |
| Layer | 9 |
d_model | 4096 |
n_features (d_sae) | 65536 |
| Activation | TopK, k=128 |
| Training tokens | ~10M (n_tokens=9998336) |
| Train steps | 24410 |
| Dead features | 0% |
| Dataset | ai4bharat/sangraha |
Files
sae.pt— SAE checkpointmeta.json— training metadataumap.json— 2D/3D feature embedding for visualization
- Library
- aquin
- License
- apache-2.0
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026