© 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. 52031
    Prev
    Next
    INDEX
    Explanations

    Economics, politics, history, logic

    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
    ="__
    -0.11
    ismus
    -0.10
    å¯Ł
    -0.09
    ологиÑı
    -0.09
     electr
    -0.09
    534
    -0.09
    ãĢĢl
    -0.09
     POLIT
    -0.09
    cci
    -0.09
    /Peak
    -0.08
    POSITIVE LOGITS
    ween
    0.11
    ológ
    0.11
    -cultural
    0.11
    ament
    0.10
     Rut
    0.10
    ale
    0.10
    imonial
    0.10
     Brent
    0.09
    wise
    0.09
    -admin
    0.09
    Activations Density 0.104%

    No Known Activations