© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Goodfire · Llama 3.3 70B Instruct SAE
    5. Llama3.3-70B-IT
    7. Resid Post
    9. 50-RESID-POST-GF
    llama3.3-70b-it · 50-resid-post-gf
    Source from llama3.3-70b-it-gf · Resid Post · Layer 50
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    No Configuration Found

    Search via Inference

    Run Example Search

    Search TopK by Token

    0%
    1%
    10%
    100%

    Search Explanations

    Browse

    Features in LLAMA3.3-70B-IT@50-resid-post-gf
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.