fix notebook link

README.md

@@ -43,17 +43,17 @@ From a *practical* point of view, [Failspy](https://huggingface.co/failspy) show
 
 Inspired by Failspy's work, I adapted the approach to the rap use case.
 
-📓 [Notebook: Steer Llama to respond with a rap style](yo_llama.ipynb)
+📓 [Notebook: Steer Llama to respond with a rap style](steer_llama_to_rap_style.ipynb)
 
 👣 Steps
 1. Load the Llama-3-8B-Instruct model.
 2. Load 1024 examples from Alpaca (instruction dataset).
 3. Prepare a system prompt to make the model act like a rapper.
 4. Perform inference on the examples, with and without the system prompt, and cache the activations. 
-6. Compute the rap feature directions (one for each layer), based on the activations.
-7. Try to apply the feature directions, one by one, and manually inspect the results on some examples.
-8. Select the best-performing feature direction.
-9. Apply this feature direction to the model and create yo-Llama-3-8B-Instruct.
+5. Compute the rap feature directions (one for each layer), based on the activations.
+6. Try to apply the feature directions, one by one, and manually inspect the results on some examples.
+7. Select the best-performing feature direction.
+8. Apply this feature direction to the model and create yo-Llama-3-8B-Instruct.
 
 ## 🚧 Limitations of this approach
 (Maybe a trivial observation)