© 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. 464
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    $MESS
    -0.15
    YPRE
    -0.11
    $LANG
    -0.10
    gba
    -0.10
     sacr
    -0.10
    ardown
    -0.10
    IFO
    -0.10
    enting
    -0.10
    anto
    -0.10
    ↵↵
    -0.09
    kea
    -0.09
     orient
    -0.09
    istrovství
    -0.09
    478
    -0.09
    afil
    -0.09
    股东
    -0.09
    oron
    -0.09
    �
    -0.09
    KANJI
    -0.09
     blackColor
    -0.09
    Positive Logits
    LETTE
    0.11
     sos
    0.10
    ieri
    0.10
    actal
    0.10
     Nun
    0.10
    errer
    0.09
    anian
    0.09
    ASET
    0.09
    annes
    0.09
     div
    0.09
    blick
    0.09
     coping
    0.09
    式
    0.09
    bek
    0.09
    zag
    0.09
     privilege
    0.09
     nun
    0.09
    pone
    0.09
     NU
    0.09
    inker
    0.09
    Activations Density 50.277%
    Loading dashboard...