© 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. 80982
    Prev
    Next
    INDEX
    Explanations

    references to health and dietary choices related to sugars and food options

    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
     кад
    -0.07
    dot
    -0.06
    лÑĮÑĤ
    -0.06
     Deals
    -0.06
     community
    -0.06
    DEPTH
    -0.06
    whel
    -0.06
    zan
    -0.06
    869
    -0.05
     capture
    -0.05
    POSITIVE LOGITS
     foods
    0.08
    /***/
    0.07
     intake
    0.07
    iefs
    0.07
    ès
    0.07
    zheimer
    0.07
    items
    0.07
    ;element
    0.07
    rella
    0.07
    WAYS
    0.07
    Activations Density 0.005%

    No Known Activations