© 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. 82958
    Prev
    Next
    INDEX
    Explanations

    references to "pie," often in various contexts related to food or metaphorical uses

    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
    ooke
    -0.07
    t
    -0.07
     Shelf
    -0.07
    ynos
    -0.07
    rello
    -0.07
     beams
    -0.07
    leck
    -0.07
    νÏĮ
    -0.06
    typings
    -0.06
    ization
    -0.06
    POSITIVE LOGITS
     pie
    0.08
    uvre
    0.07
    cem
    0.07
    Pie
    0.07
    zas
    0.07
     PIE
    0.06
    ãģĸ
    0.06
    cake
    0.06
     Wie
    0.06
    cing
    0.06
    Activations Density 0.013%

    No Known Activations