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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26475
    Prev
    Next
    INDEX
    Explanations

    numbers and references to scientific studies or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    alian
    -0.06
    odes
    -0.06
    readcrumbs
    -0.06
     Lauderdale
    -0.06
    licant
    -0.06
    èĬĿ
    -0.06
     Moines
    -0.06
    lications
    -0.06
    odie
    -0.06
    ока
    -0.06
    POSITIVE LOGITS
     Dün
    0.07
    .abstract
    0.07
    ìĶ
    0.07
     dán
    0.07
    GIN
    0.07
    SOR
    0.07
    à¥ģà¤
    0.07
    IELD
    0.06
    .Reporting
    0.06
    OKIE
    0.06
    Activations Density 0.007%

    No Known Activations