© 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. 53528
    Prev
    Next
    INDEX
    Explanations

    answer or possibility

    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
     Ged
    -0.08
     aload
    -0.08
    enson
    -0.08
    (æ°´
    -0.08
    ::::::::::
    -0.08
    aldi
    -0.08
    roscope
    -0.08
    ustum
    -0.07
    apol
    -0.07
    ilate
    -0.07
    POSITIVE LOGITS
     answer
    1.03
     answers
    0.84
    answer
    0.79
    çŃĶæ¡Ī
    0.76
     Answer
    0.73
     answered
    0.68
    Answer
    0.66
    -answer
    0.61
    _answer
    0.61
    (answer
    0.59
    Activations Density 0.463%

    No Known Activations