© 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. 449
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     prox
    -0.13
    BUG
    -0.11
     thu
    -0.10
     lo
    -0.10
     view
    -0.10
    Backing
    -0.10
    FixedSize
    -0.10
     Sole
    -0.10
    rolling
    -0.10
     processData
    -0.10
    ollen
    -0.10
     gou
    -0.10
    ADF
    -0.09
    Cog
    -0.09
     priv
    -0.09
    oten
    -0.09
    iry
    -0.09
     stereo
    -0.09
    KF
    -0.09
     kos
    -0.09
    Positive Logits
    ァ
    0.12
     Mats
    0.12
    しの
    0.11
    ewood
    0.10
     stan
    0.10
    izzle
    0.10
     Sag
    0.10
     conson
    0.10
    513
    0.10
     Farmer
    0.09
     openFileDialog
    0.09
    ＿__
    0.09
     Dodd
    0.09
    hai
    0.09
    碎
    0.09
     Halk
    0.09
     pav
    0.09
     Meyer
    0.09
    ods
    0.09
    .ut
    0.09
    Activations Density 46.446%
    Loading dashboard...