© 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. 343
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    494
    -0.10
     com
    -0.10
     NX
    -0.10
    esso
    -0.09
     op
    -0.09
    ismu
    -0.09
    rypton
    -0.09
    사회
    -0.09
    xa
    -0.09
     EDGE
    -0.09
    GBK
    -0.09
    Xã
    -0.09
     '{@
    -0.09
    ắ
    -0.09
    伴
    -0.09
    Obsolete
    -0.09
    elden
    -0.09
     bail
    -0.09
    络
    -0.09
     EVP
    -0.08
    Positive Logits
     COP
    0.10
    _mtx
    0.10
    iminal
    0.09
     Barnett
    0.09
    inish
    0.09
    ming
    0.09
     Sheridan
    0.09
     States
    0.09
     Hann
    0.09
     Nab
    0.09
     Blind
    0.09
     Lowell
    0.09
    itol
    0.09
    -cross
    0.08
     Extended
    0.08
    arth
    0.08
     Leban
    0.08
    Extended
    0.08
     Alternate
    0.08
    FT
    0.08
    Activations Density 52.235%
    Loading dashboard...