© 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. 480
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Daly
    -0.12
    bor
    -0.10
     Capture
    -0.10
    igg
    -0.10
    onet
    -0.10
    atz
    -0.10
    bis
    -0.09
    SCP
    -0.09
    undra
    -0.09
    947
    -0.09
    iedad
    -0.09
     Giles
    -0.09
     Jac
    -0.09
    vre
    -0.09
     pis
    -0.09
     divor
    -0.08
    alam
    -0.08
    ｧ
    -0.08
    某
    -0.08
    uj
    -0.08
    Positive Logits
     AB
    0.10
    icc
    0.09
    787
    0.09
    {_
    0.09
    _GL
    0.09
     Rare
    0.09
    tml
    0.09
    HEET
    0.09
    ::::::::::::::
    0.09
    .toArray
    0.09
    �
    0.09
     /:
    0.09
    arth
    0.09
    lrt
    0.09
    egree
    0.09
    erland
    0.09
     independently
    0.09
     Mant
    0.09
     |:
    0.09
    UIS
    0.09
    Activations Density 43.420%
    Loading dashboard...