© 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. 9-LLAMASCOPE-RES-131K
    11. 94764
    Prev
    Next
    INDEX
    Explanations

    food-related terms, particularly involving various types of dishes and meals

    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
     match
    -0.06
     sponge
    -0.06
    azer
    -0.06
     wr
    -0.06
    orges
    -0.06
    ore
    -0.05
    angl
    -0.05
    rov
    -0.05
    y
    -0.05
     bump
    -0.05
    POSITIVE LOGITS
    arus
    0.08
    flix
    0.08
    боÑĢ
    0.08
    icontrol
    0.08
     torino
    0.07
    inflate
    0.07
    686
    0.07
    |,↵
    0.07
    anford
    0.07
     Dixon
    0.07
    Activations Density 0.026%

    No Known Activations