© 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. 454
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Aberdeen
    -0.11
    aso
    -0.10
     Cabin
    -0.10
     ext
    -0.10
     Jord
    -0.10
    itori
    -0.10
    omo
    -0.09
    olog
    -0.09
    agem
    -0.09
     Honest
    -0.09
     {.
    -0.09
    ubat
    -0.09
    grid
    -0.09
    čan
    -0.09
    portun
    -0.09
     permanent
    -0.09
     age
    -0.08
    577
    -0.08
    üst
    -0.08
    light
    -0.08
    Positive Logits
    oken
    0.11
    ｢
    0.11
     Gaut
    0.11
    _rp
    0.11
    亜
    0.10
    oucher
    0.10
    chwitz
    0.10
    FILENAME
    0.10
     Brock
    0.10
    _／
    0.10
     Brun
    0.09
    ucker
    0.09
    ￣｀
    0.09
     Guild
    0.09
     Kut
    0.09
    ậy
    0.09
     Rus
    0.09
    FindBy
    0.09
    τζ
    0.09
    _IV
    0.09
    Activations Density 51.626%
    Loading dashboard...