Update README.md

README.md

@@ -13,7 +13,7 @@ tags:
 
 A SAE (Sparse Autoencoder) for [deepseek-ai/DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B).
 
-It is trained specifically on layer 48 of DeepSeek-R1-Distill-Llama-8B and achieves a final L0 of 36. 
+It is trained specifically on layer 48 of DeepSeek-R1-Distill-Llama-70B and achieves a final L0 of 36. 
 
 This model is used to decompose Llama's activations into interpretable features.