© 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. 29339
    Prev
    Next
    INDEX
    Explanations

    becoming president, focusing on, natural languages

    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
     DataAccess
    -0.10
    iets
    -0.08
     Cher
    -0.08
    اÙĥÙĨ
    -0.08
    .definition
    -0.08
    /*č\n
    -0.08
    bolt
    -0.08
    rych
    -0.08
    .TODO
    -0.08
    olt
    -0.08
    POSITIVE LOGITS
     obvious
    0.11
     core
    0.10
     commitment
    0.10
    558
    0.09
     focus
    0.09
    zu
    0.09
    æł¸å¿ĥ
    0.09
    umo
    0.09
     lies
    0.09
    ád
    0.09
    Activations Density 0.004%

    No Known Activations