© 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. 106470
    Prev
    Next
    INDEX
    Explanations

    phrases indicating meals or food-related activities

    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
    ying
    -0.07
    ihar
    -0.06
    fen
    -0.06
    fade
    -0.06
    imas
    -0.06
    ipes
    -0.06
    blur
    -0.06
    EPROM
    -0.06
    lsi
    -0.06
    imens
    -0.06
    POSITIVE LOGITS
     breakfast
    0.07
    lack
    0.06
     governor
    0.06
     sust
    0.06
    867
    0.06
    .statusText
    0.06
    ĵn
    0.06
    ãĤ¸ãĤª
    0.06
    _via
    0.06
    ä»ģ
    0.06
    Activations Density 0.012%

    No Known Activations