© 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. 336
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ass
    -0.10
     ocas
    -0.10
     Tay
    -0.10
    RootElement
    -0.10
     NE
    -0.10
     Weekend
    -0.09
    iêu
    -0.09
    tem
    -0.09
    ocache
    -0.09
    _parms
    -0.09
     assim
    -0.09
    yc
    -0.09
    iffe
    -0.09
     sen
    -0.09
    fuse
    -0.09
     :|:
    -0.09
     Legs
    -0.09
    ups
    -0.09
     Pillow
    -0.09
    杂
    -0.09
    Positive Logits
     chalk
    0.12
    chalk
    0.11
     nymph
    0.10
    �
    0.10
    erra
    0.10
    esters
    0.09
    ＝
    0.09
    �
    0.09
    itty
    0.09
     elders
    0.09
    apas
    0.09
    berger
    0.09
     OB
    0.09
     launcher
    0.09
    ouro
    0.09
    loo
    0.09
    bour
    0.08
    OSP
    0.08
     Gad
    0.08
    _qty
    0.08
    Activations Density 47.608%
    Loading dashboard...