© 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. 125629
    Prev
    Next
    INDEX
    Explanations

    mentions of car brands and models, particularly focusing on Chevrolet, Volkswagen, and other automobile manufacturers

    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
    erdale
    -0.06
    asz
    -0.06
     Dane
    -0.06
    jango
    -0.06
    ELLOW
    -0.06
    Entre
    -0.06
    elman
    -0.06
    ellow
    -0.06
     Ferrari
    -0.06
    ergus
    -0.06
    POSITIVE LOGITS
    /Linux
    0.08
    -logo
    0.07
    家çļĦ
    0.07
    -Benz
    0.07
    cairo
    0.07
    -Russian
    0.07
    zhou
    0.07
    _logo
    0.07
     logo
    0.07
    룬ìĬ¤
    0.07
    Activations Density 0.010%

    No Known Activations