© 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. 18040
    Prev
    Next
    INDEX
    Explanations

    references to global health issues and programs

    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
     جاÙĨ
    -0.07
     Loy
    -0.06
    ito
    -0.06
    loy
    -0.06
    yleft
    -0.06
    меÑĩ
    -0.06
    implify
    -0.06
    culus
    -0.06
    ény
    -0.06
    ategorical
    -0.06
    POSITIVE LOGITS
     global
    0.18
    global
    0.16
     worldwide
    0.15
     world
    0.15
     Global
    0.14
    Global
    0.14
     globally
    0.13
     GLOBAL
    0.13
    ä¸ĸçķĮ
    0.13
    _global
    0.13
    Activations Density 0.091%

    No Known Activations