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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96100
    Prev
    Next
    INDEX
    Explanations

    topics related to health, specifically concerning treatment and disease outbreaks

    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
    ynamo
    -0.06
    crete
    -0.06
    853
    -0.06
    UBY
    -0.06
    scriptId
    -0.06
    mlink
    -0.06
    ky
    -0.05
    éĢ£
    -0.05
    æĶ¯
    -0.05
    616
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģ¯
    0.08
    ÙĬÙĩ
    0.07
     Michaels
    0.07
    اÙģØª
    0.07
    _PRINTF
    0.07
    æ±½
    0.07
    éĢł
    0.06
    stanov
    0.06
    ncy
    0.06
    ãģķãģĦ
    0.06
    Activations Density 0.021%

    No Known Activations