© 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. 486
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Laud
    -0.11
    ibal
    -0.10
     Tome
    -0.10
    ayout
    -0.09
    (::
    -0.09
    drv
    -0.09
    /Library
    -0.09
     Leisure
    -0.09
    eten
    -0.08
     Realm
    -0.08
    ipherals
    -0.08
    _like
    -0.08
    jom
    -0.08
     solo
    -0.08
     saf
    -0.08
     Ri
    -0.08
    anzi
    -0.08
     modern
    -0.08
    ewan
    -0.08
    /jav
    -0.08
    Positive Logits
     Doll
    0.10
    ∠
    0.10
     suce
    0.10
    ece
    0.10
    KeyValue
    0.10
    umd
    0.10
     Grill
    0.10
    견
    0.10
     Schneider
    0.10
    pir
    0.10
    ufs
    0.09
    ogue
    0.09
    zig
    0.09
    tu
    0.09
    uzu
    0.09
    AGING
    0.09
    �
    0.09
     hypers
    0.09
    suite
    0.09
    ugin
    0.09
    Activations Density 54.414%
    Loading dashboard...