© 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. 87864
    Prev
    Next
    INDEX
    Explanations

    associations between healthcare, pharmaceutical terms, and the roles of various stakeholders in the healthcare supply chain

    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
    ercial
    -0.08
    acher
    -0.07
     ç¤
    -0.07
    .Xaml
    -0.07
    .createFrom
    -0.07
    KeySpec
    -0.07
    ©
    -0.07
    ÛĮÚ©ÛĮ
    -0.07
    _exports
    -0.07
     teammate
    -0.07
    POSITIVE LOGITS
     provider
    0.07
     others
    0.07
     accessory
    0.06
     anc
    0.06
     Educational
    0.06
    endon
    0.06
     service
    0.06
     third
    0.06
    attery
    0.06
     umbrella
    0.06
    Activations Density 0.027%

    No Known Activations