© 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. 316
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    OwnProperty
    -0.10
    adlo
    -0.10
    SKIP
    -0.10
     inversion
    -0.10
     ar
    -0.10
    务
    -0.10
     intr
    -0.10
     Ton
    -0.10
     Hacker
    -0.10
    osy
    -0.09
     incons
    -0.09
     Tos
    -0.09
     cass
    -0.09
    legates
    -0.09
    STITUTE
    -0.09
     middle
    -0.09
     SKIP
    -0.09
    ginas
    -0.09
     Cassidy
    -0.09
    στε
    -0.09
    Positive Logits
     Bra
    0.11
     Civic
    0.11
     Spl
    0.11
    ibur
    0.11
     spl
    0.11
     coma
    0.10
     Fallon
    0.10
    alker
    0.10
    圳
    0.10
    ander
    0.10
    轮
    0.10
    communic
    0.10
     Pitch
    0.10
     tr
    0.10
     harness
    0.10
    Insets
    0.09
    ulet
    0.09
    ­
    0.09
    coma
    0.09
    .Serializable
    0.09
    Activations Density 61.603%
    Loading dashboard...