© 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. 457
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Clay
    -0.12
    ewis
    -0.12
    -tooltip
    -0.11
    kip
    -0.11
     Hess
    -0.10
    �
    -0.10
     Tears
    -0.10
     deduct
    -0.10
    antro
    -0.09
    TouchUpInside
    -0.09
     flat
    -0.09
     actual
    -0.09
    pbs
    -0.09
     clay
    -0.09
     Clayton
    -0.09
     tele
    -0.09
     inheritance
    -0.09
     Attribute
    -0.09
     Schn
    -0.09
    pare
    -0.09
    Positive Logits
     vh
    0.10
     Cran
    0.10
     tran
    0.10
    곡
    0.10
    iasm
    0.10
    avor
    0.10
    ابعة
    0.10
    egen
    0.10
     HttpMethod
    0.10
     Rath
    0.09
    isman
    0.09
     �
    0.09
     Spicer
    0.09
    onda
    0.09
    reas
    0.09
    逐
    0.09
     disqualified
    0.09
    ophobia
    0.09
    �
    0.09
     Lantern
    0.09
    Activations Density 48.102%
    Loading dashboard...