Update README.md

README.md

@@ -277,6 +277,10 @@ logits, kv_cache, features = llama_3_1_8b.forward(
 print(llama_3_1_8b.tokenizer.decode(logits[-1].argmax(-1)))
 ```
 
+## Training
+
+Trained on activations harvested from Llama-3.3-70B-Instruct on the [LMSYS-Chat-1M dataset](https://arxiv.org/pdf/2309.11998).
+
 ## Responsibility & Safety
 
 Safety is at the core of everything we do at Goodfire. As a public benefit