© 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. 38484
    Prev
    Next
    INDEX
    Explanations

    nationality profession

    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
     playwright
    -0.10
     unnamed
    -0.10
    iв
    -0.09
     å¤
    -0.09
     Playoff
    -0.09
    iants
    -0.09
     Bowling
    -0.09
     CURLOPT
    -0.09
     jadx
    -0.09
     bowling
    -0.08
    POSITIVE LOGITS
     American
    0.14
     pop
    0.14
     act
    0.13
     actor
    0.13
     ë°°ìļ°
    0.12
     professional
    0.12
     akt
    0.12
    act
    0.12
     Twitch
    0.12
     television
    0.12
    Activations Density 0.206%

    No Known Activations