© 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. 384
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ätt
    -0.09
     Dre
    -0.09
    �
    -0.09
     gent
    -0.09
     onstage
    -0.09
    379
    -0.08
     OTHERWISE
    -0.08
     sco
    -0.08
    ihan
    -0.08
     Belg
    -0.08
    antee
    -0.08
     crater
    -0.08
    ania
    -0.08
     writ
    -0.08
     Andr
    -0.08
    Bomb
    -0.08
     concern
    -0.08
    Defaults
    -0.08
    ecer
    -0.08
     Tub
    -0.08
    Positive Logits
     pant
    0.12
     Pant
    0.10
    odo
    0.09
     orig
    0.09
    igure
    0.09
    ollapsed
    0.09
    ↵
    0.09
     adm
    0.09
    orre
    0.09
    ODO
    0.09
    ecies
    0.09
    Bindable
    0.09
     Wer
    0.08
     Tyr
    0.08
    .mdl
    0.08
    _fixture
    0.08
    arkin
    0.08
    sr
    0.08
     Cin
    0.08
    weg
    0.08
    Activations Density 46.374%
    Loading dashboard...