© 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. 63282
    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
    chor
    -0.08
    岡
    -0.07
    ç¯Ģ
    -0.07
    .buf
    -0.07
    ÑĪка
    -0.06
    rvine
    -0.06
    -tm
    -0.06
    hurst
    -0.06
    asename
    -0.06
    aines
    -0.06
    POSITIVE LOGITS
     equ
    0.07
    aram
    0.06
    hem
    0.06
    üst
    0.06
     cast
    0.06
     sag
    0.06
     promised
    0.06
    ol
    0.06
    pras
    0.06
    ÑĢок
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.