© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127737
    Prev
    Next
    INDEX
    Explanations

    terms related to medical risk factors and patient safety

    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
    rlen
    -0.09
    emoc
    -0.08
    /Instruction
    -0.07
    ortho
    -0.07
    entai
    -0.07
    umas
    -0.07
    irse
    -0.07
    ÑĥÑĪки
    -0.07
    ãģįãģª
    -0.07
    INTR
    -0.07
    POSITIVE LOGITS
     risk
    0.08
     Risk
    0.07
     target
    0.07
     cholesterol
    0.07
    -risk
    0.06
     Lifestyle
    0.06
     lifestyle
    0.06
     heart
    0.06
     OW
    0.06
    0.06
    Activations Density 0.004%

    No Known Activations