© 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. 314
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Sax
    -0.11
    ila
    -0.10
    igu
    -0.09
     Armen
    -0.09
    Berry
    -0.09
    coni
    -0.09
    acular
    -0.09
    (Mat
    -0.09
     Mehr
    -0.09
    icast
    -0.09
    ingo
    -0.09
     batching
    -0.09
    ocking
    -0.09
    bero
    -0.09
     ramp
    -0.09
     conven
    -0.09
    lh
    -0.09
    deaux
    -0.09
     jel
    -0.09
     feeding
    -0.09
    Positive Logits
     Jed
    0.12
     Walton
    0.12
     pec
    0.11
     Dit
    0.11
    ozem
    0.11
     Yaz
    0.10
     tunnel
    0.10
     cane
    0.10
    LAB
    0.10
    hir
    0.10
    unk
    0.10
     Canal
    0.10
    /lab
    0.10
     tunnels
    0.10
     X
    0.10
     geometry
    0.10
     literal
    0.09
    ekt
    0.09
     (*((
    0.09
     hey
    0.09
    Activations Density 47.878%
    Loading dashboard...