© 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. 46035
    Prev
    Next
    INDEX
    Explanations

    code formatting and structure

    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
     Garner
    -0.11
     Garland
    -0.10
    lander
    -0.09
     Burk
    -0.09
     Lloyd
    -0.09
    346
    -0.08
    -INF
    -0.08
     Burton
    -0.08
    aken
    -0.08
    oi
    -0.08
    POSITIVE LOGITS
    à¹Ĩ
    0.09
    UBE
    0.09
     Mush
    0.09
    ë²Ī
    0.09
     Wich
    0.08
     humane
    0.08
    ipe
    0.08
    blas
    0.08
     Warren
    0.08
     Hill
    0.08
    Activations Density 0.037%

    No Known Activations