© 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. 323
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    �
    -0.11
     Saunders
    -0.11
    236
    -0.10
    .openConnection
    -0.10
     lump
    -0.10
    egl
    -0.10
    reater
    -0.10
    agate
    -0.10
     Vern
    -0.09
    nila
    -0.09
    eam
    -0.09
    hetto
    -0.09
    .ops
    -0.09
    apia
    -0.09
    481
    -0.09
    oa
    -0.09
     Liberation
    -0.09
     Roose
    -0.09
     paginate
    -0.09
    ivate
    -0.09
    Positive Logits
     two
    0.18
     three
    0.14
    two
    0.11
     sal
    0.11
    iyi
    0.11
    两个
    0.11
     Kang
    0.10
     Disclaimer
    0.10
     four
    0.10
     Two
    0.10
     several
    0.10
     zwei
    0.10
     five
    0.10
    .appspot
    0.09
    ��
    0.09
     favor
    0.09
     kang
    0.09
     gating
    0.09
     Svens
    0.09
    245
    0.09
    Activations Density 55.211%
    Loading dashboard...