© 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. 494
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Dav
    -0.12
     Ling
    -0.11
    amba
    -0.10
    595
    -0.10
    �
    -0.10
     ent
    -0.10
    estr
    -0.09
     Maz
    -0.09
    　ノ
    -0.09
     Pas
    -0.09
    ent
    -0.09
    _issues
    -0.09
     demon
    -0.09
     mage
    -0.09
    avery
    -0.09
     rig
    -0.09
     Carm
    -0.09
    uth
    -0.09
     Range
    -0.09
    583
    -0.09
    Positive Logits
    enson
    0.12
    322
    0.11
    neider
    0.10
    ヾ
    0.10
    aterno
    0.10
    DE
    0.10
    堂
    0.10
    imed
    0.10
    647
    0.10
    rams
    0.10
     Bere
    0.10
     pha
    0.09
     Joi
    0.09
    ﾟ
    0.09
    orent
    0.09
     Bid
    0.09
    utor
    0.09
    215
    0.09
    structural
    0.09
    mits
    0.09
    Activations Density 53.582%
    Loading dashboard...