© 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. 392
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    969
    -0.11
     Natal
    -0.10
    esel
    -0.09
     Foley
    -0.09
    bero
    -0.09
    jom
    -0.09
    iffer
    -0.09
    /stdc
    -0.08
    836
    -0.08
     Fever
    -0.08
    lsi
    -0.08
    awn
    -0.08
    -Trump
    -0.08
     Wel
    -0.08
     Dam
    -0.08
    аду
    -0.08
    oma
    -0.08
     buc
    -0.08
    839
    -0.08
    anon
    -0.08
    Positive Logits
    šk
    0.10
    ACP
    0.09
    ина
    0.09
    asca
    0.09
    sembles
    0.09
     Conj
    0.09
    rahim
    0.09
     Marks
    0.09
     tran
    0.08
    賀
    0.08
     conj
    0.08
    掌
    0.08
     Fried
    0.08
     transf
    0.08
    祭
    0.08
    Marks
    0.08
     McConnell
    0.08
     Elli
    0.08
    upos
    0.08
    Gravity
    0.08
    Activations Density 47.722%
    Loading dashboard...