© 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. 129921
    Prev
    Next
    INDEX
    Explanations

    references to food and drink products, particularly those related to Asian cuisine

    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
    UGE
    -0.07
    ÑĢеÑĪ
    -0.07
    abbage
    -0.07
    Pie
    -0.07
    ropa
    -0.07
    dition
    -0.07
    xico
    -0.06
    udi
    -0.06
    oftware
    -0.06
     Pie
    -0.06
    POSITIVE LOGITS
     product
    0.12
     brand
    0.11
     products
    0.11
     brands
    0.11
    product
    0.10
    -product
    0.09
    brands
    0.09
    产åĵģ
    0.08
    products
    0.08
    (product
    0.08
    Activations Density 0.274%

    No Known Activations