© 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. 55046
    Prev
    Next
    INDEX
    Explanations

    food items and their descriptions within a meal context

    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
    iba
    -0.08
    acr
    -0.07
    -archive
    -0.06
     Axis
    -0.06
    ase
    -0.06
    .glob
    -0.06
    ummy
    -0.06
     tenants
    -0.06
     ÑģоÑĢ
    -0.06
    veal
    -0.06
    POSITIVE LOGITS
     breakfast
    0.14
     morning
    0.13
     Breakfast
    0.13
     mornings
    0.13
     brunch
    0.11
     Morning
    0.10
    Morning
    0.10
     sunrise
    0.10
     ìķĦ침
    0.09
     Eggs
    0.09
    Activations Density 0.039%

    No Known Activations