© 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. 377
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     continent
    -0.11
     shock
    -0.11
     Fool
    -0.10
    Mgr
    -0.09
     LICENSE
    -0.09
     means
    -0.09
    ode
    -0.09
     boom
    -0.09
     recovery
    -0.09
    anger
    -0.09
     Groups
    -0.09
    �
    -0.09
    atsu
    -0.09
    .Groups
    -0.09
     Boom
    -0.09
    ifi
    -0.09
    tron
    -0.09
     def
    -0.09
     Pratt
    -0.09
    �
    -0.09
    Positive Logits
     ｰ
    0.15
     tang
    0.12
     Blo
    0.11
    �
    0.11
     fro
    0.10
    сли
    0.10
    HttpException
    0.10
    warts
    0.10
    folk
    0.10
    abase
    0.09
     Tang
    0.09
    /sdk
    0.09
     Eag
    0.09
    cko
    0.09
    ucken
    0.09
    ignon
    0.09
    /trans
    0.09
    ullo
    0.09
     �
    0.09
     federal
    0.09
    Activations Density 59.790%
    Loading dashboard...