© 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. 87594
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations and entitlements in social contexts

    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
     FOOD
    -0.10
     meals
    -0.10
    é£Łåĵģ
    -0.09
     lunch
    -0.09
     dinners
    -0.09
    Food
    -0.08
     lunches
    -0.08
    à¸Ńาหาร
    -0.08
    .food
    -0.08
     Cuisine
    -0.08
    POSITIVE LOGITS
    active
    0.06
     entertainment
    0.06
    ect
    0.06
    graph
    0.06
    بÙĪÙĦ
    0.06
     entertain
    0.06
    clo
    0.06
    ockets
    0.06
     clothes
    0.06
    fax
    0.06
    Activations Density 0.078%

    No Known Activations