© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14318
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Ster
    -0.06
     seper
    -0.05
    umph
    -0.05
     aff
    -0.05
     void
    -0.05
    -0.05
     lev
    -0.05
     rein
    -0.05
    obody
    -0.05
     t
    -0.05
    POSITIVE LOGITS
    дина
    0.08
    ocket
    0.08
    ONGL
    0.08
    åħ¬åijĬ
    0.08
    æµģéĩı
    0.07
    lamaz
    0.07
    .gs
    0.07
    amespace
    0.07
    ãģ¾ãģļ
    0.07
    dden
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.