© 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. 362
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     ー
    -0.12
     oppos
    -0.11
     equival
    -0.11
    holm
    -0.11
    rok
    -0.09
    ixon
    -0.09
    rač
    -0.09
    mpi
    -0.09
     fals
    -0.09
     takeaway
    -0.09
     verst
    -0.09
     bright
    -0.09
    ring
    -0.09
     superhero
    -0.09
    ニア
    -0.09
    abox
    -0.09
    onth
    -0.09
    /GL
    -0.09
     TBD
    -0.08
    ainter
    -0.08
    Positive Logits
     Vir
    0.11
    Vir
    0.10
     Voice
    0.10
     Neck
    0.10
     unc
    0.10
    �
    0.09
    :async
    0.09
    乎
    0.09
    mint
    0.09
     distant
    0.09
     Rowe
    0.09
    -neck
    0.09
     Chic
    0.09
     Tile
    0.09
    _MISC
    0.09
    ayas
    0.09
    iosa
    0.09
     Compatible
    0.09
     stor
    0.09
     extrav
    0.09
    Activations Density 44.420%
    Loading dashboard...