© 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. 399
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    errar
    -0.10
     Mund
    -0.09
    idy
    -0.09
     Haram
    -0.09
    Subscribe
    -0.09
    enic
    -0.09
    figcaption
    -0.09
    flen
    -0.09
    _INSTANCE
    -0.09
    ippets
    -0.09
    kh
    -0.09
     dunk
    -0.08
     familiar
    -0.08
     franchises
    -0.08
    ings
    -0.08
    ago
    -0.08
    zed
    -0.08
     Frank
    -0.08
     exper
    -0.08
    kdir
    -0.08
    Positive Logits
    mt
    0.10
    (cf
    0.09
    owell
    0.09
    nard
    0.09
    appen
    0.09
     above
    0.09
    mia
    0.09
     EINVAL
    0.09
    mos
    0.09
    achuset
    0.09
    　　 　 　 　
    0.09
    ota
    0.09
    ossa
    0.09
     GridLayout
    0.09
    -src
    0.09
    езульт
    0.09
    _Util
    0.09
     Sor
    0.09
    stad
    0.09
    趣
    0.09
    Activations Density 55.737%
    Loading dashboard...