© 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. 369
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     moments
    -0.15
     elements
    -0.12
     areas
    -0.11
     pockets
    -0.11
     moment
    -0.11
     parts
    -0.11
    也有
    -0.11
     exceptions
    -0.11
    /moment
    -0.10
     manifest
    -0.10
     Ke
    -0.10
     momentos
    -0.10
     gig
    -0.10
     Moment
    -0.10
     Moments
    -0.10
     Stephen
    -0.09
    ocoder
    -0.09
    Cls
    -0.09
     fle
    -0.09
     specific
    -0.09
    Positive Logits
    omor
    0.12
     Went
    0.10
     strm
    0.10
     somewhat
    0.10
     Slam
    0.10
    igid
    0.10
    Conditions
    0.10
    (ERR
    0.10
    +len
    0.09
    aload
    0.09
    cale
    0.09
    _WM
    0.09
    alie
    0.09
     else
    0.09
    TERM
    0.09
    ROME
    0.09
    irket
    0.09
     Yaş
    0.09
    ped
    0.09
     〈
    0.08
    Activations Density 49.880%
    Loading dashboard...