© 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. 466
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    SSI
    -0.10
     acc
    -0.10
    HM
    -0.09
     crunch
    -0.09
    abeth
    -0.09
    apers
    -0.09
     stip
    -0.09
     HM
    -0.09
    �
    -0.09
    bron
    -0.09
     Hipp
    -0.09
     Paper
    -0.08
    serter
    -0.08
     pract
    -0.08
    benh
    -0.08
    abay
    -0.08
    235
    -0.08
    ented
    -0.08
    ofi
    -0.08
    rror
    -0.08
    Positive Logits
    978
    0.11
    orny
    0.11
     fitte
    0.10
    annes
    0.10
    (Unknown
    0.10
    
    0.10
     Harbor
    0.10
    rez
    0.09
     bunk
    0.09
     Sellers
    0.09
    らせ
    0.09
     onCancelled
    0.09
     copp
    0.09
     oppon
    0.09
    
    0.09
     Mediterr
    0.09
     Broadcast
    0.09
     Dunk
    0.09
    oste
    0.09
    succ
    0.09
    Activations Density 51.548%
    Loading dashboard...