© 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. 105262
    Prev
    Next
    INDEX
    Explanations

    references to dental hygiene products and concepts

    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
    ÏĤ
    -0.09
    hift
    -0.08
    hire
    -0.07
    帯
    -0.07
    боÑĢа
    -0.07
    ovich
    -0.07
    ndl
    -0.07
    ytt
    -0.07
    inand
    -0.07
    Åijs
    -0.07
    POSITIVE LOGITS
    paste
    0.10
    brush
    0.09
     latter
    0.08
    less
    0.07
    ress
    0.07
    iele
    0.07
    ie
    0.07
    .LENGTH
    0.07
    asted
    0.06
    son
    0.06
    Activations Density 0.003%

    No Known Activations