Posts tagged "superposition"
3 posts
Where Does a Language Model Think? Finding and Removing the 'Workspace' Layers of Llama-3.1-8B
*A hands-on interpretability walkthrough. We watch concepts form layer-by-layer inside Llama-3.1-8B-Instruct, measure precisely which layers carry meaning, then **delete layers** — one at a time and
Double Descent Explained: Why More Data Can Make a Model Worse
window.MathJax = { tex: { inlineMath: [['$','$'], ['\\(','\\)']], displayMath: [['$$','$$'], ['\\[','\\]']] }, svg: { fontCache: 'global' } };  Inside a neural network, a single neuron fires for many unrelated things at once — it's **po