© 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. 400
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    asad
    -0.11
    imenti
    -0.10
     Gren
    -0.10
    alama
    -0.10
    ihan
    -0.10
    ecer
    -0.10
     Sims
    -0.10
    .IsNullOr
    -0.10
     uniquely
    -0.10
    MetaData
    -0.09
    otti
    -0.09
    tep
    -0.09
    itive
    -0.09
     addCriterion
    -0.09
    PILE
    -0.09
    ypress
    -0.09
    //{{
    -0.09
    �
    -0.09
    ussen
    -0.09
     cler
    -0.09
    Positive Logits
    DEX
    0.11
    TF
    0.11
     mysterious
    0.10
    bart
    0.10
     stead
    0.10
    ếu
    0.10
    oola
    0.09
    ading
    0.09
     Strand
    0.09
    亡
    0.09
     Reeves
    0.09
     mystery
    0.09
    atural
    0.09
     trough
    0.09
     why
    0.09
     Aim
    0.09
    888
    0.09
    ennent
    0.09
     lawy
    0.09
     Jade
    0.09
    Activations Density 56.397%
    Loading dashboard...