© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11497
    Prev
    Next
    INDEX
    Explanations

    ato or atuação

    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
    Negative Logits
    owed
    -0.11
    ITS
    -0.09
    crast
    -0.09
    tram
    -0.09
    OKIE
    -0.09
    ILE
    -0.09
    ohn
    -0.09
    URES
    -0.08
    hook
    -0.08
    HS
    -0.08
    POSITIVE LOGITS
    enu
    0.14
    itudes
    0.12
    itude
    0.12
    outs
    0.12
    ENTION
    0.12
    wood
    0.12
    &T
    0.11
    temp
    0.11
    letic
    0.11
    aque
    0.11
    Activations Density 0.015%

    No Known Activations