© 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 EvalsExportsAPI 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. 82834
    Prev
    Next
    INDEX
    Explanations

    mentions of breakfast foods and related items

    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
    añ
    -0.06
    _SYS
    -0.06
     octave
    -0.06
    ç»ĵ
    -0.06
    craft
    -0.06
     function
    -0.05
     vap
    -0.05
     Empire
    -0.05
     meat
    -0.05
    avin
    -0.05
    POSITIVE LOGITS
     breakfast
    0.12
     morning
    0.11
     Breakfast
    0.11
     mornings
    0.11
    Morning
    0.10
     Morning
    0.10
    onder
    0.07
    porno
    0.07
     cereal
    0.07
     ìķĦ침
    0.07
    Activations Density 0.011%

    No Known Activations