© 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. 16285
    Prev
    Next
    INDEX
    Explanations

    patterns related to hydration and fluid intake

    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
    ubble
    -0.07
     sulfur
    -0.07
     HEAP
    -0.06
    urch
    -0.06
    umbo
    -0.06
    imli
    -0.06
    agr
    -0.06
    digest
    -0.06
    BLE
    -0.06
    floating
    -0.06
    POSITIVE LOGITS
     water
    0.17
    water
    0.15
     Water
    0.14
     hydration
    0.14
    _water
    0.13
    Water
    0.13
    æ°´
    0.13
    -water
    0.13
     hydr
    0.13
     parch
    0.13
    Activations Density 0.045%

    No Known Activations