© 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. 334
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    �
    -0.11
     Cors
    -0.10
     Rico
    -0.10
    inho
    -0.10
    onders
    -0.10
    VOKE
    -0.09
     flick
    -0.09
    äh
    -0.09
    403
    -0.09
    .geo
    -0.09
    apus
    -0.09
     Dw
    -0.09
     LAB
    -0.09
     inher
    -0.09
     grantResults
    -0.09
    PCP
    -0.09
     rio
    -0.09
     trusts
    -0.09
    献
    -0.09
    �
    -0.09
    Positive Logits
     cr
    0.14
     acc
    0.13
     Junction
    0.12
    stakes
    0.11
     Christie
    0.11
     Wich
    0.11
     harmon
    0.10
    テル
    0.10
     var
    0.10
     Amit
    0.10
    Mounted
    0.10
     Hitch
    0.10
     Streams
    0.09
    翔
    0.09
     ser
    0.09
    Streams
    0.09
    osa
    0.09
     precious
    0.09
    destruct
    0.09
    uner
    0.09
    Activations Density 57.290%
    Loading dashboard...