© 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. 478
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ctl
    -0.11
    dera
    -0.10
    -s
    -0.10
    bek
    -0.10
    �
    -0.10
    bh
    -0.10
    orc
    -0.09
     Lust
    -0.09
     fact
    -0.09
    ection
    -0.09
     Fare
    -0.09
    447
    -0.09
    944
    -0.09
     clim
    -0.09
    bine
    -0.09
     tipping
    -0.09
    454
    -0.08
     smoke
    -0.08
     stitch
    -0.08
    bac
    -0.08
    Positive Logits
     Pam
    0.11
     Elo
    0.10
    alette
    0.10
    ￥
    0.10
    ＼
    0.10
    emen
    0.10
     EXP
    0.10
    繁
    0.10
     foreground
    0.10
    fcn
    0.10
    朋
    0.10
    orage
    0.09
    oot
    0.09
     Watt
    0.09
    _hierarchy
    0.09
    igar
    0.09
    ullet
    0.09
     extravag
    0.09
     sergeant
    0.09
     Memory
    0.09
    Activations Density 51.813%
    Loading dashboard...