© 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. 394
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    atr
    -0.12
     discret
    -0.11
    ascript
    -0.10
     Dish
    -0.10
     Strait
    -0.10
     Kem
    -0.10
     ALT
    -0.09
     passed
    -0.09
    aset
    -0.09
    erus
    -0.09
    reamble
    -0.09
    uky
    -0.09
    andy
    -0.09
    atri
    -0.09
    aces
    -0.09
     Vul
    -0.09
     puta
    -0.09
     Crescent
    -0.09
    UTE
    -0.09
    .endpoint
    -0.09
    Positive Logits
     tou
    0.10
    /misc
    0.10
     pile
    0.09
     Transitional
    0.09
     MN
    0.09
    liğinde
    0.09
     Ner
    0.09
     Hubbard
    0.09
     aure
    0.09
    ofs
    0.09
     mob
    0.09
     movement
    0.09
    nesc
    0.09
    abbage
    0.09
    _paint
    0.09
    immel
    0.09
     piled
    0.09
     chained
    0.09
    phins
    0.09
     personals
    0.09
    Activations Density 52.909%
    Loading dashboard...