© 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. 397
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     dub
    -0.11
     Dub
    -0.10
    onec
    -0.10
    orca
    -0.10
     tog
    -0.10
    tml
    -0.10
     Byrne
    -0.10
    graphics
    -0.10
     Crowley
    -0.10
    ugar
    -0.09
    室
    -0.09
    �
    -0.09
    meeting
    -0.09
     Chill
    -0.09
    idon
    -0.09
    渡
    -0.09
     baggage
    -0.09
    薄
    -0.09
    Dub
    -0.09
    oner
    -0.09
    Positive Logits
     law
    0.11
     Law
    0.10
     cap
    0.10
     Giles
    0.10
    lee
    0.10
     Total
    0.09
    109
    0.09
     Rum
    0.09
     Serialized
    0.09
    apyrus
    0.09
     dy
    0.09
     Maul
    0.09
    orsche
    0.09
     Lloyd
    0.08
    kü
    0.08
    護
    0.08
    _attached
    0.08
     Lect
    0.08
     Boh
    0.08
     Cour
    0.08
    Activations Density 41.815%
    Loading dashboard...