Update README.md

README.md

@@ -22,7 +22,7 @@ over large language model operations.
 
 __Model Creator__: [Goodfire](https://huggingface.co/Goodfire), built to work with [Meta's Llama models](https://huggingface.co/meta-llama)
 
-By using __Goodfire/Llama-3.1-8B-Instruct__model.layers.19__ you agree to the [LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct/blob/main/LICENSE)
+By using __Goodfire/Llama-3.1-8B-Instruct-SAE-l19__ you agree to the [LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct/blob/main/LICENSE)
 
 
 ## Intended Use
@@ -65,4 +65,7 @@ We trained our SAE on activations harvested from Llama-3.1-8B-Instruct on the [L
 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/).
+
+Toxic features were removed prior to the release of this SAE. If you are a safety researcher that 
+would like access to the features we’ve removed, you can reach out at <a href="mailto:[email protected]">[email protected]</a> for access.