© 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. 376
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Bran
    -0.11
     Rent
    -0.10
     zev
    -0.10
     Luz
    -0.10
     ips
    -0.10
     IPs
    -0.10
    DH
    -0.10
     McGu
    -0.09
     Heller
    -0.09
    PM
    -0.09
    .removeAttribute
    -0.09
    ADO
    -0.09
     Dah
    -0.09
     Wid
    -0.09
     Kob
    -0.09
     Reign
    -0.09
     irres
    -0.09
    �
    -0.09
    otec
    -0.09
     Orientation
    -0.09
    Positive Logits
     pub
    0.12
    abay
    0.11
    aupt
    0.10
    eking
    0.10
     self
    0.10
    classNames
    0.10
     cat
    0.10
     dood
    0.10
     arch
    0.09
     cru
    0.09
     ged
    0.09
    /GL
    0.09
     subtype
    0.09
    　ﾞ
    0.09
    นาน
    0.09
    ibu
    0.09
    *>*
    0.09
    coop
    0.09
    ucci
    0.09
     fab
    0.09
    Activations Density 57.882%
    Loading dashboard...