© 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. 484
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    itori
    -0.11
    acco
    -0.10
    　l
    -0.10
    enburg
    -0.10
     Newport
    -0.10
     cue
    -0.09
    pan
    -0.09
     Strip
    -0.09
     Rings
    -0.09
    ahy
    -0.09
     Shame
    -0.09
     Vance
    -0.09
    ISC
    -0.09
    usk
    -0.09
    -alist
    -0.09
    ped
    -0.09
    zilla
    -0.08
     поступ
    -0.08
    乙
    -0.08
    imers
    -0.08
    Positive Logits
    リカ
    0.11
    481
    0.10
     Laud
    0.10
     Leap
    0.10
    ifax
    0.10
    _objs
    0.10
    MaxY
    0.09
     Piet
    0.09
     rever
    0.09
    errer
    0.09
    yme
    0.09
    CancelButton
    0.09
    Leap
    0.09
    ien
    0.09
     leap
    0.09
     :.:
    0.09
     inade
    0.09
     Chop
    0.08
     heg
    0.08
     Herald
    0.08
    Activations Density 54.813%
    Loading dashboard...