© 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. 391
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     bod
    -0.10
    CFG
    -0.10
    iaux
    -0.10
     Fog
    -0.10
     Nec
    -0.10
     �
    -0.10
     random
    -0.10
     suit
    -0.10
    hots
    -0.10
     bab
    -0.09
    IFS
    -0.09
    梯
    -0.09
     Fear
    -0.09
     unre
    -0.09
     ho
    -0.09
     sho
    -0.09
     fog
    -0.09
     Wander
    -0.09
     fingerprint
    -0.09
     Richmond
    -0.09
    Positive Logits
     electr
    0.11
     |/
    0.10
     Lodge
    0.10
     hrd
    0.10
     Pussy
    0.10
     Ness
    0.10
     Holl
    0.10
    uls
    0.09
    eb
    0.09
    /commons
    0.09
    ्यवस
    0.09
     nett
    0.09
    �
    0.09
    asion
    0.09
    Wunused
    0.09
    duk
    0.09
     Nile
    0.09
    ynos
    0.09
    acus
    0.09
     Maiden
    0.09
    Activations Density 53.774%
    Loading dashboard...