© 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. 381
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    /do
    -0.11
     crown
    -0.11
     Rouge
    -0.11
    cela
    -0.10
    ̣
    -0.10
    ゝ
    -0.10
    oyo
    -0.10
    804
    -0.10
    inalg
    -0.10
    baugh
    -0.09
     angel
    -0.09
    izioni
    -0.09
     kra
    -0.09
     nap
    -0.09
     fetisch
    -0.09
    inne
    -0.09
     harms
    -0.09
    -----↵↵
    -0.09
    ulos
    -0.09
    dl
    -0.09
    Positive Logits
     Ecc
    0.11
     Charlie
    0.11
    infer
    0.10
     Emil
    0.10
    ery
    0.10
     regress
    0.10
    acob
    0.10
     jung
    0.09
    ofile
    0.09
    α
    0.09
     variants
    0.09
    ăng
    0.09
    blank
    0.09
    yt
    0.09
    .coordinate
    0.09
    ongo
    0.09
     Blank
    0.09
    regor
    0.09
    tero
    0.09
    気持ち
    0.09
    Activations Density 46.585%
    Loading dashboard...