© 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. 71268
    Prev
    Next
    INDEX
    Explanations

    information related to health benefits and properties of specific substances

    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
    ｡
    -0.07
    keit
    -0.07
    üz
    -0.07
    raison
    -0.06
    otron
    -0.06
    pis
    -0.06
    nict
    -0.06
    füh
    -0.06
    utomation
    -0.06
     weather
    -0.06
    POSITIVE LOGITS
     SHIPPING
    0.07
    apesh
    0.06
     rat
    0.06
     researchers
    0.06
     mour
    0.06
    roker
    0.06
     study
    0.06
    nano
    0.06
    hoot
    0.06
     rats
    0.06
    Activations Density 0.011%

    No Known Activations