© 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. 373
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     hal
    -0.15
     Hal
    -0.14
    hal
    -0.10
    ibr
    -0.10
    Hal
    -0.10
     Ellis
    -0.10
     Hale
    -0.10
    .uk
    -0.10
    ies
    -0.09
    agon
    -0.09
     BR
    -0.09
     popul
    -0.09
    als
    -0.09
     tr
    -0.09
    397
    -0.09
    341
    -0.09
    al
    -0.09
    bie
    -0.09
     uk
    -0.09
     SSR
    -0.08
    Positive Logits
     exh
    0.12
     Hurt
    0.11
    acom
    0.11
    ше
    0.11
     Lehr
    0.10
    ﾟ
    0.10
     Scar
    0.10
     VARIABLE
    0.10
    -refresh
    0.10
     cous
    0.10
    rost
    0.10
    kiye
    0.10
    pcs
    0.09
    UPPORTED
    0.09
     Horton
    0.09
     Hopkins
    0.09
    ignet
    0.09
     Folding
    0.09
    _SCR
    0.09
    ohl
    0.09
    Activations Density 45.723%
    Loading dashboard...