© 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. 416
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     sharing
    -0.12
     Sharing
    -0.11
    Sharing
    -0.11
    -sharing
    -0.10
     Shared
    -0.10
    sharing
    -0.10
     Shield
    -0.10
     shared
    -0.10
    alion
    -0.10
    afil
    -0.09
    挑
    -0.09
     blow
    -0.09
    vio
    -0.09
     Soda
    -0.09
    .share
    -0.09
    ema
    -0.09
     natives
    -0.09
    407
    -0.09
    -pocket
    -0.09
     purple
    -0.09
    Positive Logits
    iani
    0.12
     Mais
    0.11
    ﾍ
    0.10
    rut
    0.10
     inconvenient
    0.10
    ebb
    0.10
     Parties
    0.10
     harness
    0.10
    ridor
    0.09
     IllegalStateException
    0.09
    actable
    0.09
     Malk
    0.09
     )↵↵↵↵↵↵↵↵
    0.09
    кут
    0.09
    -fw
    0.09
    ongo
    0.09
    805
    0.09
     subt
    0.09
    大全
    0.09
    izza
    0.09
    Activations Density 45.584%
    Loading dashboard...