© 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. 119420
    Prev
    Next
    INDEX
    Explanations

    terms related to stress and its physiological effects on the body

    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
    ych
    -0.08
    rary
    -0.08
    vier
    -0.08
    ulan
    -0.07
    _argv
    -0.07
    idad
    -0.07
     Barney
    -0.07
    нÑĤ
    -0.07
     vess
    -0.07
    LOUD
    -0.07
    POSITIVE LOGITS
     adaptations
    0.07
     response
    0.07
    response
    0.06
     alarm
    0.06
     arch
    0.06
    .activation
    0.06
     activated
    0.06
     mobil
    0.06
     activation
    0.06
     responses
    0.06
    Activations Density 0.004%

    No Known Activations