© 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. 78701
    Prev
    Next
    INDEX
    Explanations

    terms related to emergency protocols and health information accessibility

    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
    è³Ģ
    -0.08
    apiro
    -0.07
    imbus
    -0.06
    yte
    -0.06
    /stats
    -0.06
     nguyên
    -0.06
    алов
    -0.06
    ình
    -0.06
    ç¥
    -0.06
    unsch
    -0.06
    POSITIVE LOGITS
     tubes
    0.07
    .setDefault
    0.07
     pall
    0.07
     Tubes
    0.07
     medical
    0.06
     tube
    0.06
     death
    0.06
     dying
    0.06
    åĨ³
    0.06
     Record
    0.06
    Activations Density 0.002%

    No Known Activations