© 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. 74147
    Prev
    Next
    INDEX
    Explanations

    topics related to configuring and managing SharePoint authentication and authorization

    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
    storybook
    -0.07
    processable
    -0.07
    .scenes
    -0.07
    /***/
    -0.07
     Äįi
    -0.07
    .streaming
    -0.07
     nebu
    -0.06
    Touchable
    -0.06
    542
    -0.06
    EMPLARY
    -0.06
    POSITIVE LOGITS
     using
    0.07
     Advanced
    0.06
    еÑģÑĤи
    0.06
    iens
    0.06
     recap
    0.06
     ëĭ¤ìĸijíķľ
    0.06
    using
    0.06
     advanced
    0.06
    _advanced
    0.06
    estar
    0.05
    Activations Density 0.008%

    No Known Activations