Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5233
    Prev
    Next
    INDEX
    Explanations

    keywords related to cooking and food preparation

    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
    shint
    -0.06
    fen
    -0.06
     Dough
    -0.06
    statt
    -0.06
    bread
    -0.06
     Alternative
    -0.06
     dough
    -0.06
     Bread
    -0.06
     alternative
    -0.06
     sel
    -0.06
    POSITIVE LOGITS
     sauce
    0.12
     stew
    0.12
     curry
    0.11
     gravy
    0.11
     Sauce
    0.11
     sauces
    0.10
     Curry
    0.09
     simmer
    0.08
     tomato
    0.08
     broth
    0.07
    Activations Density 0.046%

    No Known Activations