© 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. 341
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Alias
    -0.11
    udo
    -0.10
     plast
    -0.10
    iras
    -0.10
    bower
    -0.10
    asy
    -0.10
    wang
    -0.10
     Fon
    -0.10
     disciplined
    -0.09
     Maj
    -0.09
    arde
    -0.09
     hon
    -0.09
     Tune
    -0.09
     multic
    -0.09
    //:
    -0.09
     Dro
    -0.09
     bot
    -0.09
    ield
    -0.09
     Lester
    -0.09
     artwork
    -0.09
    Positive Logits
     followed
    0.12
    enschaft
    0.11
    zano
    0.11
     Din
    0.11
    BaseContext
    0.10
    zers
    0.10
    pii
    0.10
    oose
    0.10
    атку
    0.10
    omo
    0.10
     collaps
    0.10
    rike
    0.10
    umer
    0.10
    ｉ
    0.10
    -eye
    0.10
    uters
    0.10
    _LOGGER
    0.10
    /moment
    0.10
    Τα
    0.10
    ippy
    0.10
    Activations Density 52.670%
    Loading dashboard...