© 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. 76940
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical analysis and patient trajectories in medical research

    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
    #
    -0.08
    TYPO
    -0.07
    .DataTable
    -0.07
     dán
    -0.07
    اء
    -0.07
    agli
    -0.07
    prob
    -0.07
    alace
    -0.07
    먹
    -0.07
    меÑĩ
    -0.07
    POSITIVE LOGITS
    astro
    0.06
     regions
    0.06
     effects
    0.06
    {{{
    0.06
     assertion
    0.06
     significance
    0.06
    ôle
    0.05
    icken
    0.05
     Rob
    0.05
    elfare
    0.05
    Activations Density 0.034%

    No Known Activations