© 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. 337
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    /--
    -0.14
     McCoy
    -0.11
    orf
    -0.11
    adt
    -0.10
    amin
    -0.10
    azio
    -0.10
    835
    -0.10
    lez
    -0.10
    ("--
    -0.10
    adera
    -0.10
    __.__
    -0.10
     DateTimeOffset
    -0.09
     Sac
    -0.09
    itesse
    -0.09
    inox
    -0.09
    iness
    -0.09
     Geh
    -0.09
     (--
    -0.09
    ết
    -0.09
    odo
    -0.09
    Positive Logits
     Huss
    0.11
     hors
    0.10
    omba
    0.10
    elho
    0.10
    dem
    0.10
    نسا
    0.09
     �
    0.09
    vod
    0.09
    istrovství
    0.09
    dims
    0.09
    ::_
    0.09
    ardy
    0.09
     McMahon
    0.09
     Hans
    0.09
    UserData
    0.08
     Perm
    0.08
    orent
    0.08
     Thomson
    0.08
     �
    0.08
     bare
    0.08
    Activations Density 35.297%
    Loading dashboard...