© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    young girl in anime

    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
     Sabb
    -0.12
     Crosby
    -0.11
     Sultan
    -0.11
     Cros
    -0.10
     Flex
    -0.09
    urs
    -0.09
     Realm
    -0.09
     Voor
    -0.09
    ä¸ģ
    -0.09
     ãģı
    -0.09
    POSITIVE LOGITS
     Evangel
    0.15
     pilots
    0.14
     pil
    0.11
     Eva
    0.11
     evangel
    0.11
     Huck
    0.11
     Neon
    0.10
    ãĥ
    0.10
     Angel
    0.10
    ETO
    0.10
    Activations Density 0.020%

    No Known Activations