© 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. 414
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     ．
    -0.13
     phục
    -0.11
     clockwise
    -0.10
     Charles
    -0.10
    (ang
    -0.10
    enate
    -0.10
     Items
    -0.10
    jev
    -0.10
     Daniels
    -0.10
    rollo
    -0.09
     yıldır
    -0.09
     ho
    -0.09
    _fault
    -0.09
     Rico
    -0.09
     itemCount
    -0.09
    :variables
    -0.09
    ::$
    -0.09
    ycz
    -0.09
    AndServe
    -0.09
     recip
    -0.09
    Positive Logits
    alc
    0.10
    gate
    0.10
    rl
    0.10
    ileo
    0.10
     Bark
    0.09
    (
    0.09
    ies
    0.09
    lee
    0.09
    341
    0.09
    g
    0.09
     Heller
    0.09
     Rog
    0.09
     arena
    0.09
    -
    0.09
    lam
    0.08
     stray
    0.08
     Mans
    0.08
    sg
    0.08
    med
    0.08
     shim
    0.08
    Activations Density 42.999%
    Loading dashboard...