© 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. 85347
    Prev
    Next
    INDEX
    Explanations

    terms related to medical testing and treatment efficacy

    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
    Å¡ti
    -0.07
     aggreg
    -0.07
    ieme
    -0.07
    .tencent
    -0.06
     isim
    -0.06
    ạm
    -0.06
    Ĺı
    -0.06
    StateChanged
    -0.06
     pii
    -0.06
    анка
    -0.06
    POSITIVE LOGITS
    gent
    0.07
    anja
    0.07
     con
    0.06
     age
    0.06
    elder
    0.06
     Concurrent
    0.06
     score
    0.06
     Electoral
    0.06
     concurrent
    0.06
    apy
    0.06
    Activations Density 0.032%

    No Known Activations