© 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. 325
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    suffix
    -0.10
     applied
    -0.09
     Older
    -0.09
    asa
    -0.09
    uros
    -0.09
     Watson
    -0.09
    -labelledby
    -0.09
    SCR
    -0.09
     Gad
    -0.09
     Pond
    -0.09
    dden
    -0.08
    ibal
    -0.08
    -liter
    -0.08
     Schro
    -0.08
     older
    -0.08
    ウン
    -0.08
    tl
    -0.08
    aya
    -0.08
    Bounding
    -0.08
     torch
    -0.08
    Positive Logits
    ouz
    0.11
     octave
    0.10
    awns
    0.10
    keeper
    0.10
    偶
    0.10
     Donovan
    0.10
     jit
    0.10
    409
    0.10
    第一次
    0.10
     Nass
    0.10
    olars
    0.09
    ANCH
    0.09
     Wass
    0.09
    盛
    0.09
     Sext
    0.09
    ��
    0.09
     Brady
    0.09
    لان
    0.09
    gang
    0.09
    642
    0.09
    Activations Density 52.976%
    Loading dashboard...