© 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. 328
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    view
    -0.11
     ad
    -0.11
    sap
    -0.10
     view
    -0.10
     displ
    -0.10
    oya
    -0.10
     mode
    -0.10
     Orr
    -0.09
    atak
    -0.09
    essler
    -0.09
    -､
    -0.09
    abwe
    -0.09
     mir
    -0.09
     lib
    -0.09
     defaults
    -0.09
    VIEW
    -0.09
    PIN
    -0.09
    lotte
    -0.09
    Mir
    -0.09
    anas
    -0.09
    Positive Logits
     �
    0.10
     IRC
    0.10
    ami
    0.10
     trav
    0.09
    �
    0.09
    peater
    0.09
    лик
    0.09
    /forum
    0.09
    813
    0.09
    �
    0.09
    ponge
    0.09
    стю
    0.09
     nut
    0.09
    udoku
    0.09
     quot
    0.09
     selves
    0.09
     sty
    0.08
     sponge
    0.08
    ediator
    0.08
    �
    0.08
    Activations Density 41.310%
    Loading dashboard...