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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82530
    Prev
    Next
    INDEX
    Explanations

    words related to culinary or food-related terms

    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
    اÙĨÙĩ
    -0.09
    cape
    -0.07
    kening
    -0.07
    hud
    -0.07
    esty
    -0.07
    usto
    -0.07
    /problems
    -0.07
    .LayoutStyle
    -0.07
    elpers
    -0.07
     kå
    -0.07
    POSITIVE LOGITS
    -shaped
    0.08
    ated
    0.07
    à¸Ĺà¸Ńà¸ĩ
    0.07
    head
    0.06
    etak
    0.06
     dated
    0.06
     wearer
    0.06
    works
    0.06
     suspense
    0.05
     principal
    0.05
    Activations Density 0.066%

    No Known Activations