© 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. 4705
    Prev
    Next
    INDEX
    Explanations

    compelling narratives or arguments in various contexts

    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
    ưỡng
    -0.07
    culate
    -0.07
    apo
    -0.07
    нки
    -0.07
    icle
    -0.07
    eming
    -0.07
    Advisor
    -0.07
    eger
    -0.07
     Degrees
    -0.07
    wan
    -0.07
    POSITIVE LOGITS
    ments
    0.07
    ly
    0.07
     irresist
    0.06
     ìĤ¬íķŃ
    0.06
    shire
    0.06
    ingly
    0.06
    chan
    0.06
    antly
    0.06
     annum
    0.06
    ìł¸
    0.06
    Activations Density 0.008%

    No Known Activations