Update README.md

README.md

@@ -4,6 +4,9 @@ language:
 - en
 base_model:
 - meta-llama/Llama-3.3-70B-Instruct
+tags:
+- mechanistic interpretability
+- sparse autoencoder
 ---
 
 ## Model Information
@@ -36,11 +39,7 @@ To explore the feature labels check out the [Goodfire Ember SDK](https://www.goo
 The SDK provides an intuitive interface for interacting with these 
 features, allowing you to investigate how Llama processes information 
 and even steer its behavior. Get started with feature 
-exploration at [docs.goodfire.ai](https://docs.goodfire.ai) or install directly via:
-
-```
-pip install goodfire
-```
+exploration at [docs.goodfire.ai](https://docs.goodfire.ai).
 
 ## How to use
 
@@ -281,4 +280,4 @@ print(llama_3_1_8b.tokenizer.decode(logits[-1].argmax(-1)))
 Safety is at the core of everything we do at Goodfire. As a public benefit 
 corporation, we’re dedicated to understanding AI models to enable safer, more reliable 
 generative AI. You can read more about our comprehensive approach to 
-safety and responsible development in our detailed [safety overview](https://www.goodfire.ai/blog/our-approach-to-safety/). 
+safety and responsible development in our detailed [safety overview](https://www.goodfire.ai/blog/our-approach-to-safety/).