© 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. 367
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    entiful
    -0.11
     Sunder
    -0.11
    �
    -0.11
    841
    -0.11
    partment
    -0.11
     Ara
    -0.10
    onaut
    -0.10
    亭
    -0.10
    ingleton
    -0.10
    rys
    -0.10
     PTS
    -0.10
    lide
    -0.10
     unjust
    -0.10
    роничес
    -0.10
     conqu
    -0.10
     Lug
    -0.10
     Samp
    -0.09
    424
    -0.09
     Laure
    -0.09
    reck
    -0.09
    Positive Logits
    ollo
    0.11
    Runner
    0.10
    thro
    0.10
    heimer
    0.10
    /commons
    0.10
    kok
    0.10
    arb
    0.10
     Uns
    0.09
    illy
    0.09
    hr
    0.09
     Solomon
    0.09
     Barnett
    0.09
    klad
    0.09
     Race
    0.09
    TimeStamp
    0.09
    oul
    0.09
    fq
    0.09
     Solic
    0.09
    _utilities
    0.09
    uts
    0.08
    Activations Density 48.162%
    Loading dashboard...