© 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. 497
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     repl
    -0.12
    660
    -0.11
    aco
    -0.10
    ulus
    -0.10
    andon
    -0.10
    airs
    -0.10
    venta
    -0.10
     Gaul
    -0.10
    riot
    -0.09
    раг
    -0.09
    革
    -0.09
     Camel
    -0.09
    ago
    -0.09
     Hur
    -0.09
    amen
    -0.09
    scr
    -0.09
     buz
    -0.09
     Mehr
    -0.09
     Lynn
    -0.09
    ormap
    -0.09
    Positive Logits
     ​​
    0.10
    /goto
    0.10
    _fs
    0.10
    ipples
    0.10
     Tran
    0.10
     Truy
    0.10
     col
    0.10
     Gross
    0.10
    ｉ
    0.10
     ens
    0.10
    ::::::::::::
    0.10
     nich
    0.10
    .wik
    0.10
    vfs
    0.10
     gross
    0.09
     tran
    0.09
     Grain
    0.09
     Cage
    0.09
    .fromFunction
    0.09
    apus
    0.09
    Activations Density 55.106%
    Loading dashboard...