© 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. 15-LLAMASCOPE-RES-131K
    11. 103811
    Prev
    Next
    INDEX
    Explanations

    phrases related to health risks or medical concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments that indicate or emphasize the severity of risks, negative health effects, or harmful consequences, particularly in health and safety contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    [Double
    -0.07
    ÐĴÑĸд
    -0.07
    erator
    -0.07
    yro
    -0.06
    plits
    -0.06
    åłĤ
    -0.06
    ednou
    -0.06
     enthus
    -0.06
    plit
    -0.06
    ymce
    -0.06
    POSITIVE LOGITS
     medical
    0.07
     effects
    0.07
    IMS
    0.06
     serious
    0.06
    medical
    0.06
     depending
    0.06
     éĸ
    0.06
    Effects
    0.06
     Alarm
    0.06
    Alarm
    0.06
    Activations Density 0.022%

    No Known Activations