© 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. 69022
    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
    bak
    -0.06
    asto
    -0.06
    boss
    -0.06
    ÑģÑĥ
    -0.06
    rape
    -0.06
     corporation
    -0.06
    incinn
    -0.06
    539
    -0.06
    inus
    -0.06
     sou
    -0.06
    POSITIVE LOGITS
    esda
    0.07
     late
    0.07
     GENERIC
    0.07
    :new
    0.07
    .epam
    0.07
    ãĥª
    0.06
    _Desc
    0.06
    late
    0.06
    -league
    0.06
    漫
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.