© 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. 38878
    Prev
    Next
    INDEX
    Explanations

    Leonard Hofstadter, feet flat, minor premises

    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
    vÄĽÅĻ
    -0.08
    _EXTERN
    -0.07
     Blasio
    -0.07
    éĺ³åŁİ
    -0.07
    erken
    -0.07
    ÃĹ</
    -0.07
     uom
    -0.07
     JADX
    -0.06
    LEC
    -0.06
    (<?
    -0.06
    POSITIVE LOGITS
    .moveToNext
    0.07
    contador
    0.07
    .RELATED
    0.07
     mne
    0.07
    bersome
    0.07
     Hector
    0.07
    ì§Ģëħ¸
    0.06
    sında
    0.06
    eria
    0.06
    оÑĢаÑı
    0.06
    Activations Density 0.982%

    No Known Activations