© 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. 382
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    .git
    -0.11
     Ber
    -0.10
     Tanz
    -0.10
    atis
    -0.09
    zh
    -0.09
     Tah
    -0.09
    at
    -0.09
     wil
    -0.09
     pit
    -0.09
     Patrol
    -0.08
     reporters
    -0.08
    its
    -0.08
     Mitar
    -0.08
    zdy
    -0.08
     Dashboard
    -0.08
     Caval
    -0.08
     thermometer
    -0.08
     Sel
    -0.08
     tract
    -0.08
     Accountability
    -0.08
    Positive Logits
    istrovství
    0.13
     consenting
    0.12
    ￣｀
    0.11
    Jake
    0.11
     rhe
    0.11
    inkel
    0.11
    _SA
    0.11
    ©©
    0.11
    ��
    0.11
    �
    0.11
    Youtube
    0.11
     vidé
    0.10
    _cube
    0.10
    cü
    0.10
    andalone
    0.10
    VRT
    0.10
     Wass
    0.10
     multip
    0.10
    .MixedReality
    0.10
     双线
    0.10
    Activations Density 51.655%
    Loading dashboard...