Mistral-Small-3.2-24B-Instruct-2506-SAE
This model is a sparse autoencoder and decoder trained on the 30th activation layer of Mistral-Small-3.2-24B-Instruct-2506.
- Downloads last month
- 9
Safetensors
Model size
3B params
Tensor type
F32
·
Model tree for Codcordance/Mistral-Small-3.2-24B-Instruct-2506-SAE
Base model
mistralai/Mistral-Small-3.1-24B-Base-2503