© 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. 313
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     chrono
    -0.10
    680
    -0.10
    áb
    -0.09
    967
    -0.09
     tri
    -0.09
     alist
    -0.09
     Coul
    -0.09
    682
    -0.09
     Parent
    -0.09
     sag
    -0.09
    itous
    -0.09
     BCH
    -0.09
     Noah
    -0.09
    956
    -0.09
    ‡
    -0.09
    enko
    -0.09
    955
    -0.09
    TemplateName
    -0.09
    andy
    -0.08
     Jam
    -0.08
    Positive Logits
     gratuites
    0.11
     Schwe
    0.11
    ernes
    0.10
     Milton
    0.10
    agra
    0.10
    erm
    0.10
     UIAlert
    0.10
    AdapterManager
    0.10
    fully
    0.10
     DateFormatter
    0.10
    aler
    0.09
     pare
    0.09
    _delegate
    0.09
    APO
    0.09
     Wend
    0.09
    #
    0.09
     prov
    0.09
     Verg
    0.09
     frontier
    0.09
     Cla
    0.09
    Activations Density 49.086%
    Loading dashboard...