© 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. 309
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     medium
    -0.11
     addCriterion
    -0.11
     Nero
    -0.10
     Medium
    -0.10
     Dum
    -0.09
     compromise
    -0.09
     bo
    -0.09
    abit
    -0.09
    erner
    -0.09
     شر
    -0.09
    ird
    -0.09
    635
    -0.09
    JM
    -0.09
     Tas
    -0.09
     Tear
    -0.09
     klu
    -0.09
    _dl
    -0.08
     spinner
    -0.08
     pron
    -0.08
    ›
    -0.08
    Positive Logits
     �
    0.11
    oyer
    0.11
    elia
    0.10
    etter
    0.10
    .Border
    0.10
    เลย
    0.10
     Skip
    0.10
     premature
    0.10
    inki
    0.10
     disp
    0.10
    摩
    0.10
     Demir
    0.10
    遇
    0.09
     Moss
    0.09
    feit
    0.09
    .libs
    0.09
    ayah
    0.09
     onBind
    0.09
     Assistance
    0.09
     Grimm
    0.09
    Activations Density 59.081%
    Loading dashboard...