© 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. 64932
    Prev
    Next
    INDEX
    Explanations

    entropy of convex functions

    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
     Leban
    -0.10
     asympt
    -0.10
    uze
    -0.09
     invers
    -0.09
    inverse
    -0.09
    हल
    -0.09
    alian
    -0.09
    oha
    -0.08
    -password
    -0.08
    orgot
    -0.08
    POSITIVE LOGITS
     conc
    0.16
    conc
    0.16
    åĩ
    0.15
     upper
    0.15
     Mon
    0.15
     convex
    0.14
     mon
    0.14
     Conc
    0.13
    -mon
    0.13
     increasing
    0.12
    Activations Density 0.038%

    No Known Activations