© 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. 327
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     cloth
    -0.11
     Schul
    -0.11
     bomb
    -0.10
    onte
    -0.10
     Skyl
    -0.09
    ptron
    -0.09
    eland
    -0.09
    241
    -0.09
    ument
    -0.09
     Atom
    -0.09
    ptrdiff
    -0.09
     cruc
    -0.09
    pez
    -0.09
    ̆
    -0.09
    문의
    -0.09
     Cloth
    -0.09
     DIY
    -0.09
    loth
    -0.09
     Mall
    -0.09
    251
    -0.09
    Positive Logits
    ampie
    0.10
     Thur
    0.09
     Phon
    0.09
    IGN
    0.09
    iper
    0.09
     cooper
    0.09
    ritis
    0.09
     serg
    0.08
     Tim
    0.08
    anki
    0.08
     Hera
    0.08
    _FC
    0.08
     gossip
    0.08
    ty
    0.08
     Warranty
    0.08
    ccoli
    0.08
     Turk
    0.08
    ace
    0.08
    Viewer
    0.08
    uta
    0.08
    Activations Density 49.749%
    Loading dashboard...