© 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. 19197
    Prev
    Next
    INDEX
    Explanations

    sweet, innocent-looking human

    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
    俺ãģ¯
    -0.14
     alive
    -0.10
     cazzo
    -0.10
     glory
    -0.10
    ouv
    -0.10
    _EOL
    -0.09
     fuck
    -0.09
    ãģłãģª
    -0.09
     kid
    -0.09
     god
    -0.09
    POSITIVE LOGITS
     silly
    0.14
     cute
    0.12
     hor
    0.12
     yummy
    0.12
     darn
    0.11
     sill
    0.10
     Cute
    0.10
     lots
    0.10
    icky
    0.10
    ~
    0.10
    Activations Density 0.076%

    No Known Activations