© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27352
    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
    Not in Any Lists

    No Comments

    Negative Logits
     seperate
    -0.07
    gend
    -0.07
    InBackground
    -0.07
    gratis
    -0.07
    ÙĨÛĮÙĨ
    -0.06
    openhagen
    -0.06
     Böyle
    -0.06
    mé
    -0.06
    lyn
    -0.06
    глÑıд
    -0.06
    POSITIVE LOGITS
     Vulcan
    0.06
     detriment
    0.06
     Dude
    0.06
     cards
    0.06
    ych
    0.06
     resort
    0.06
     onSave
    0.06
    adele
    0.06
     Kart
    0.05
     elabor
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.