© 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. 345
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     fault
    -0.12
     responsibility
    -0.11
     Sour
    -0.10
     reflection
    -0.10
    olla
    -0.10
     gob
    -0.10
     Bud
    -0.10
    assin
    -0.10
     Moss
    -0.10
     Kel
    -0.09
     reflected
    -0.09
    iday
    -0.09
    undi
    -0.09
    oden
    -0.09
    _cores
    -0.09
     blame
    -0.09
     reflections
    -0.09
     mun
    -0.09
     Bret
    -0.09
     Franken
    -0.09
    Positive Logits
    ahoma
    0.12
    unga
    0.11
    ＝＝
    0.11
    itan
    0.11
     Gener
    0.10
     Bul
    0.10
     "::
    0.10
     slots
    0.10
     Anders
    0.09
    ानम
    0.09
    ียบ
    0.09
    icamente
    0.09
    oust
    0.09
     Prod
    0.09
     deb
    0.09
    립
    0.09
    Transient
    0.09
    761
    0.09
     Marino
    0.09
    apollo
    0.09
    Activations Density 47.559%
    Loading dashboard...