© 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. 310
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ething
    -0.13
    ster
    -0.11
     Wesley
    -0.11
    awan
    -0.11
     Glam
    -0.11
    yar
    -0.10
    UNS
    -0.10
     Cyr
    -0.10
     Kw
    -0.10
    yd
    -0.10
     ifndef
    -0.10
     Rox
    -0.09
    una
    -0.09
    unt
    -0.09
    klad
    -0.09
    寸
    -0.09
    thew
    -0.09
     unbe
    -0.09
     UNS
    -0.09
    124
    -0.09
    Positive Logits
    ▏
    0.11
    esub
    0.11
     |_|
    0.11
    rie
    0.11
    _tE
    0.10
    -alist
    0.10
    .scalablytyped
    0.10
    .websocket
    0.10
    <|begin_of_text|>
    0.10
    _mC
    0.10
    岗
    0.10
    REFER
    0.10
     |--------------------------------------------------------------------------↵
    0.09
    _mE
    0.09
     Citizenship
    0.09
    pra
    0.09
    occo
    0.09
    Pad
    0.09
     Pra
    0.09
     Schmidt
    0.09
    Activations Density 47.537%
    Loading dashboard...