© 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. 448
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    iyon
    -0.12
    zie
    -0.10
     Rag
    -0.10
     eag
    -0.10
     Hogan
    -0.10
     Santana
    -0.10
     circuits
    -0.10
     �
    -0.10
     malt
    -0.10
     Demp
    -0.10
    axy
    -0.10
    958
    -0.10
    327
    -0.10
     Orig
    -0.10
     sup
    -0.10
     Freak
    -0.09
    opic
    -0.09
    whel
    -0.09
    occan
    -0.09
    acoes
    -0.09
    Positive Logits
     Dra
    0.11
    .scalablytyped
    0.11
     mod
    0.11
    alles
    0.10
    alley
    0.10
    toy
    0.10
     marvel
    0.10
    strup
    0.10
     narc
    0.10
    æk
    0.10
     Items
    0.09
     Ferguson
    0.09
     modal
    0.09
    _utilities
    0.09
    ItemSelected
    0.09
    SearchParams
    0.09
    IRQ
    0.09
     Bak
    0.09
     akci
    0.09
    aye
    0.09
    Activations Density 42.955%
    Loading dashboard...