© 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. 17-LLAMASCOPE-RES-131K
    11. 82212
    Prev
    Next
    INDEX
    Explanations

    mentions of marinades and references to the Marriott brand

    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
    æł·çļĦ
    -0.07
    aneous
    -0.07
    wards
    -0.06
    /place
    -0.06
    ocard
    -0.06
    UFFIX
    -0.06
    gee
    -0.06
    emp
    -0.06
    swire
    -0.06
    akin
    -0.06
    POSITIVE LOGITS
    mallow
    0.08
    quee
    0.08
    juana
    0.08
    ÙħÙĪÙĦ
    0.07
    quis
    0.07
    aling
    0.07
    ufen
    0.07
    èIJ½
    0.07
    bled
    0.07
    abic
    0.07
    Activations Density 0.046%

    No Known Activations