© 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. 16376
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and chronic diseases among underrepresented populations

    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
    enaire
    -0.07
    pillar
    -0.07
    ضÛĮ
    -0.07
    mant
    -0.07
    coe
    -0.07
    Alive
    -0.07
     kola
    -0.07
    odos
    -0.06
    nila
    -0.06
    imei
    -0.06
    POSITIVE LOGITS
     interfaces
    0.06
    aka
    0.06
     various
    0.06
     special
    0.06
    ults
    0.06
     fluids
    0.06
    è±Ĩ
    0.06
    Build
    0.06
     Guarantee
    0.06
     hol
    0.05
    Activations Density 0.049%

    No Known Activations