Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
sae_llama_l16_h65536 – AI Model by Zhongzhi1228 | AlphaNeural AI
You can deploy this model and start earning money today!
Zhongzhi1228
/
sae_llama_l16_h65536
like
0
sparse-autoencoder
mechanistic-interpretability
2602.10388
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Model Card for SAE
This model is a pre-trained Sparse Autoencoder (SAE) for [Llama].
Paper:
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs