© 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. 322
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     memor
    -0.11
    .Bus
    -0.09
    umi
    -0.09
     Lang
    -0.09
     Goldberg
    -0.09
    tron
    -0.09
    reten
    -0.09
    .memo
    -0.09
    adecimal
    -0.09
     Cah
    -0.09
     Ele
    -0.09
     Brut
    -0.09
    emouth
    -0.09
    iam
    -0.09
     Katz
    -0.09
    amburg
    -0.09
     Forums
    -0.09
    cie
    -0.08
     rss
    -0.08
    pert
    -0.08
    Positive Logits
    isma
    0.13
    olon
    0.11
    ��
    0.10
    �
    0.10
    strup
    0.10
     stunt
    0.10
    -db
    0.10
    огод
    0.10
     Truth
    0.09
     coveted
    0.09
    anou
    0.09
     �
    0.09
    RY
    0.09
    angelo
    0.09
    geois
    0.09
     �
    0.09
     Watts
    0.09
     Düş
    0.09
     intox
    0.09
     Protected
    0.09
    Activations Density 58.524%
    Loading dashboard...