© 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. Neuronpedia · MLP Neurons
    5. Llama3.3-70B-IT
    7. MLP Neurons - Layer 21
    9. 461
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Casino
    -0.09
     Till
    -0.08
    ＝＝
    -0.08
    FTA
    -0.08
     Trib
    -0.07
    isia
    -0.07
     Cassidy
    -0.07
     Guil
    -0.07
     transformative
    -0.07
     Chic
    -0.07
    �
    -0.07
    yyyy
    -0.07
    admin
    -0.07
     Camel
    -0.07
    horse
    -0.07
     Previously
    -0.07
    ogene
    -0.07
     Dawson
    -0.07
     Solo
    -0.06
    ー
    -0.06
    Positive Logits
    ��
    0.13
    €€
    0.12
    ��
    0.10
    �情
    0.10
    <|begin_of_text|>
    0.10
    /*
↵
    0.10
    edList
    0.09
     nø
    0.09
    .writeln
    0.09
    ******
↵
    0.09
    /kubernetes
    0.09
    ύπ
    0.09
    quist
    0.09
    �除
    0.09
     __("
    0.09
    �細
    0.09
    Архів
    0.09
     Intern
    0.09
     пож
    0.09
    elsing
    0.09
    Activations Density 65.149%
    Loading dashboard...