© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    ìľ¡
    -0.10
     behalf
    -0.10
     ÑĢаÑģпÑĢед
    -0.09
    duct
    -0.09
    ird
    -0.09
    lid
    -0.09
    upo
    -0.09
     harm
    -0.09
    IRS
    -0.08
    ollo
    -0.08
    POSITIVE LOGITS
     use
    0.32
     presence
    0.20
     иÑģполÑĮзовани
    0.18
    use
    0.18
     involvement
    0.17
     uso
    0.17
    presence
    0.16
     gebruik
    0.16
     employment
    0.15
     participation
    0.15
    Activations Density 0.032%

    No Known Activations