© 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. 333
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ＾
    -0.11
    CADE
    -0.11
     Mega
    -0.11
     Sawyer
    -0.10
    ripp
    -0.10
     Congress
    -0.10
     Fine
    -0.10
     attention
    -0.10
    tings
    -0.10
     célib
    -0.10
    ReadStream
    -0.10
    inden
    -0.10
    cak
    -0.09
     abort
    -0.09
     voters
    -0.09
    _HC
    -0.09
     Bad
    -0.09
    .onCreate
    -0.09
    _EV
    -0.09
    pollo
    -0.09
    Positive Logits
     landscape
    0.10
    elyn
    0.10
    ィ
    0.10
    IDAD
    0.10
     Barton
    0.10
    idad
    0.09
     Bless
    0.09
    adt
    0.09
     Innoc
    0.09
    olson
    0.09
    roe
    0.09
    FORMAT
    0.09
    /wiki
    0.09
    icz
    0.09
     iceberg
    0.09
     inorder
    0.09
     bow
    0.09
    ilot
    0.09
    afe
    0.08
    ahn
    0.08
    Activations Density 45.875%
    Loading dashboard...