© 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. 409
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ingleton
    -0.12
     Alta
    -0.11
     Zub
    -0.10
    Xi
    -0.10
     cors
    -0.10
    Tester
    -0.10
     Newport
    -0.10
     didSet
    -0.10
     Revised
    -0.10
    \Bridge
    -0.09
    uring
    -0.09
     Behavior
    -0.09
     behavior
    -0.09
    866
    -0.09
    CLK
    -0.09
    inges
    -0.09
    AMAGE
    -0.09
     Spielberg
    -0.09
    RenderTarget
    -0.09
     antib
    -0.09
    Positive Logits
     Cheney
    0.13
    onom
    0.11
    _accept
    0.10
    ＿＿＿
    0.10
    ult
    0.10
    shield
    0.09
    uli
    0.09
    juven
    0.09
    abal
    0.09
     ~
    0.09
     acted
    0.09
    �
    0.09
    ош
    0.09
    edef
    0.09
     med
    0.09
    ichen
    0.09
     DW
    0.09
     usr
    0.09
     ICON
    0.09
     Fury
    0.09
    Activations Density 45.546%
    Loading dashboard...