© 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. 57525
    Prev
    Next
    INDEX
    Explanations

    programming language, scientists, body, names, Chemistry, equally, non-Latin script

    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
     strSql
    -0.08
    ​\n\n
    -0.08
    ä»®
    -0.08
    ï¿
    -0.07
    .Formatter
    -0.07
    irit
    -0.07
     ​​
    -0.07
    .BackgroundImageLayout
    -0.07
    âĢIJ-
    -0.06
     //!<
    -0.06
    POSITIVE LOGITS
     tieten
    0.07
     Jaune
    0.07
     overposting
    0.07
     [âĢ¦]\n\n
    0.07
     [âĢ¦]\n
    0.06
     Ex
    0.06
     Camb
    0.06
    /Public
    0.06
    _INCLUDED
    0.06
     Terr
    0.06
    Activations Density 0.843%

    No Known Activations