© 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. 338
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    798
    -0.12
    ungi
    -0.11
     Mayo
    -0.10
     Vill
    -0.10
     Banner
    -0.10
    отов
    -0.09
    ged
    -0.09
    iller
    -0.09
     Doug
    -0.09
    alice
    -0.09
    inth
    -0.09
     wrapper
    -0.09
    elic
    -0.09
    ADIO
    -0.09
     Wrapper
    -0.09
    ´:
    -0.09
     Yok
    -0.09
     RAM
    -0.09
    �
    -0.09
    igte
    -0.08
    Positive Logits
     Shea
    0.11
     Heb
    0.11
    acades
    0.11
    /Instruction
    0.11
    NB
    0.11
    OLEAN
    0.11
     POSSIBILITY
    0.11
    alendar
    0.10
    hive
    0.10
    venge
    0.10
    obia
    0.10
    둘
    0.10
    appen
    0.10
    ain
    0.10
    bill
    0.10
    aidu
    0.10
     Pell
    0.10
     ltd
    0.10
    MimeType
    0.10
    UFFIX
    0.09
    Activations Density 49.591%
    Loading dashboard...