© 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. 462
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ov
    -0.11
     Shepard
    -0.11
    leigh
    -0.10
    ettes
    -0.10
    omin
    -0.10
    ACHI
    -0.10
    ーテ
    -0.10
     Brom
    -0.10
     Edgar
    -0.09
     typ
    -0.09
     absentee
    -0.09
    overn
    -0.09
    @hotmail
    -0.09
    ím
    -0.09
     Winston
    -0.09
    駐
    -0.09
     شي
    -0.09
    583
    -0.09
     emerg
    -0.09
    930
    -0.09
    Positive Logits
    rado
    0.09
    olver
    0.09
    _Tis
    0.09
    thon
    0.09
    ongs
    0.09
     ww
    0.09
    izzlies
    0.09
    ула
    0.09
    ofire
    0.09
    rej
    0.09
    /xhtml
    0.09
     cob
    0.09
    separator
    0.09
     Nach
    0.09
    afil
    0.09
     Mun
    0.09
    swer
    0.09
    redit
    0.08
    ystone
    0.08
    _SS
    0.08
    Activations Density 52.843%
    Loading dashboard...