© 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. 128655
    Prev
    Next
    INDEX
    Explanations

    references to restaurants or dining experiences

    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
    eneg
    -0.07
     åı¸
    -0.07
    utta
    -0.06
    mrt
    -0.06
     Sending
    -0.06
     баг
    -0.06
     Samar
    -0.06
    opher
    -0.06
     Briggs
    -0.06
    ugu
    -0.06
    POSITIVE LOGITS
     restaur
    0.07
    atter
    0.07
     location
    0.07
     restaurant
    0.07
     retail
    0.07
    avers
    0.07
     idea
    0.07
    location
    0.06
     concept
    0.06
     Restaurant
    0.06
    Activations Density 0.028%

    No Known Activations