Hacker News new | past | comments | ask | show | jobs | submit login

On a related note: recently, I released a visualization of all MLP neurons inside the llama3 8B model. Here is an example "derivative" neuron which is triggered when talking about the derivative concept.

https://neuralblog.github.io/llama3-neurons/neuron_viewer.ht...




This is insanely fun to just flip through. I found a "sex" neuron. https://neuralblog.github.io/llama3-neurons/neuron_viewer.ht...


Pretty cool. The tokens are highlighted based on the activation?


Yes, you're correct. The tokens are highlighted based on the neuron activation value, which is scaled to a range of 0 to 10.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: