© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61309
    Prev
    Next
    INDEX
    Explanations

    python libraries and modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buckley
    -0.11
     Hemisphere
    -0.10
    ubi
    -0.09
     usur
    -0.09
    erton
    -0.09
     Koch
    -0.09
    Marsh
    -0.09
     multiples
    -0.09
    asi
    -0.09
    \n
    -0.09
    POSITIVE LOGITS
    plotlib
    0.13
     )\n\n\n\n\n\n\n\n
    0.11
    /__
    0.11
    ify
    0.11
    uptools
    0.11
    .djang
    0.10
    ilib
    0.10
    plib
    0.10
    py
    0.10
    thon
    0.10
    Activations Density 0.133%

    No Known Activations