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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 74136
    Prev
    Next
    INDEX
    Explanations

    references to health-related policies and their impact on food and beverage industries

    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
    mrt
    -0.07
    ikel
    -0.07
    Hay
    -0.07
    _mov
    -0.07
    inus
    -0.07
    ä»Ķ
    -0.07
    vero
    -0.07
    ÑĦеÑĢ
    -0.07
    Specifier
    -0.07
    sap
    -0.07
    POSITIVE LOGITS
     obesity
    0.08
     weight
    0.07
     Obesity
    0.07
     children
    0.07
     fat
    0.06
     obese
    0.06
     calories
    0.06
     Children
    0.06
    ons
    0.06
     cal
    0.06
    Activations Density 0.014%

    No Known Activations