© 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. 308
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    amer
    -0.11
    elsing
    -0.11
     Jennings
    -0.10
     Abilities
    -0.10
     Trot
    -0.10
    etc
    -0.10
    edd
    -0.10
    〕
    -0.10
    tracted
    -0.10
     Classics
    -0.09
    .servers
    -0.09
     dude
    -0.09
     Portfolio
    -0.09
    �
    -0.09
    .stderr
    -0.09
     Greenwood
    -0.09
    ccoli
    -0.09
    INTR
    -0.09
     Schul
    -0.09
     portfolio
    -0.09
    Positive Logits
    leck
    0.11
    olls
    0.10
    rames
    0.10
     inp
    0.09
    itol
    0.09
    omik
    0.09
     Heb
    0.09
    489
    0.09
    agoon
    0.09
     desar
    0.09
    utos
    0.09
    414
    0.09
     �
    0.09
    suit
    0.09
     ide
    0.09
    abra
    0.09
    져
    0.09
     Cav
    0.09
     Ink
    0.08
     vide
    0.08
    Activations Density 46.282%
    Loading dashboard...