© 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. 62035
    Prev
    Next
    INDEX
    Explanations

    references to foie gras and discussions surrounding animal rights in food production

    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
    axe
    -0.07
    itt
    -0.07
    ÑĨвеÑĤ
    -0.06
    atts
    -0.06
    alles
    -0.06
     Axe
    -0.06
    rim
    -0.06
    ultip
    -0.06
     axe
    -0.06
     Dollar
    -0.06
    POSITIVE LOGITS
    olesterol
    0.07
    pus
    0.07
     productName
    0.07
    elry
    0.07
    /Gate
    0.07
    LOOD
    0.07
     fatt
    0.06
    ouis
    0.06
    ewis
    0.06
    omanip
    0.06
    Activations Density 0.019%

    No Known Activations