© 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 EvalsExportsAPI 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. 88835
    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
    .scalablytyped
    -0.07
    ngth
    -0.07
    ookies
    -0.07
    dit
    -0.06
    Č↵
    -0.06
    ptime
    -0.06
    plx
    -0.06
    ContextHolder
    -0.06
    erial
    -0.06
    aceutical
    -0.06
    POSITIVE LOGITS
    strup
    0.06
     Tyto
    0.06
     ÙĨÛĮÙħ
    0.06
    von
    0.06
    ires
    0.06
     emergency
    0.06
    KHR
    0.06
    ichel
    0.06
    empre
    0.06
    blo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.