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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76598
    Prev
    Next
    INDEX
    Explanations

    names and mentions of individuals and their impactful stories or contributions in the context of nursing

    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
    (Map
    -0.07
    à¸µà¸Ł
    -0.07
     Terrain
    -0.06
    ÙĪØ§Ø¡
    -0.06
     Map
    -0.06
    agra
    -0.06
     attendance
    -0.06
    ÏĦαι
    -0.06
    ivor
    -0.06
    644
    -0.06
    POSITIVE LOGITS
     hosts
    0.07
    cem
    0.06
     sic
    0.06
    cia
    0.06
     HOST
    0.06
     Pompe
    0.06
    addy
    0.06
    .getHost
    0.06
    PointSize
    0.06
     host
    0.06
    Activations Density 0.006%

    No Known Activations