© 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. 442
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    elop
    -0.11
    aldo
    -0.11
    ElementException
    -0.10
    .scalablytyped
    -0.10
    ！」↵↵
    -0.10
     spit
    -0.10
    addy
    -0.10
    GuidId
    -0.09
    osg
    -0.09
    CodeAt
    -0.09
    .xz
    -0.09
    -､
    -0.09
    ？」↵↵
    -0.09
    .undefined
    -0.09
     NUIT
    -0.09
    .appendTo
    -0.09
    ağ
    -0.09
     Gum
    -0.09
    inder
    -0.09
     Autor
    -0.09
    Positive Logits
    ule
    0.09
     nim
    0.09
     koc
    0.09
     Bik
    0.09
    ules
    0.09
    458
    0.08
     وق
    0.08
     Deng
    0.08
    ｨ
    0.08
     Arb
    0.08
     AAA
    0.08
     aspect
    0.08
     pys
    0.08
     Benefit
    0.08
     naz
    0.08
     jeopardy
    0.08
     Caldwell
    0.08
    6
    0.08
    naz
    0.08
    0.08
    Activations Density 58.024%
    Loading dashboard...