© 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. 422
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    HEN
    -0.13
    alaxy
    -0.11
    cpt
    -0.11
     factual
    -0.10
    abilia
    -0.10
    bum
    -0.10
    OOK
    -0.10
    ienne
    -0.09
     hen
    -0.09
    .Prop
    -0.09
    aload
    -0.09
    urve
    -0.09
    orest
    -0.09
     vur
    -0.09
    ATCH
    -0.09
    ﾏ
    -0.09
    idue
    -0.09
     Burg
    -0.09
    ook
    -0.09
     фунда
    -0.09
    Positive Logits
    elta
    0.11
     unint
    0.11
     Sik
    0.10
     Noel
    0.09
     flat
    0.09
     dear
    0.09
     Ston
    0.09
     mills
    0.09
    anou
    0.09
    案
    0.09
    �
    0.09
     matte
    0.08
    �
    0.08
    eltas
    0.08
     milliseconds
    0.08
    iqueta
    0.08
     Hawth
    0.08
     Flat
    0.08
     Pon
    0.08
     Matte
    0.08
    Activations Density 53.145%
    Loading dashboard...