© 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. 9387
    Prev
    Next
    INDEX
    Explanations

    пÑĢо пÑĢоведенной

    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
    rade
    -0.09
    icer
    -0.09
    atory
    -0.09
    iej
    -0.09
    ongan
    -0.09
    vey
    -0.09
    lest
    -0.09
    452
    -0.09
    itol
    -0.09
    arding
    -0.09
    POSITIVE LOGITS
    agma
    0.12
    ed
    0.12
    ť
    0.09
    tie
    0.09
     Tie
    0.09
    иÑģÑĮ
    0.09
    o
    0.09
     zost
    0.09
    eded
    0.09
    iena
    0.09
    Activations Density 0.104%

    No Known Activations