© 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. 116856
    Prev
    Next
    INDEX
    Explanations

    terms related to the prevalence and incidence of medical conditions

    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
    ÐIJÑĢÑħÑĸв
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ů
    -0.07
    @qq
    -0.07
    geber
    -0.07
    icap
    -0.07
    ceb
    -0.07
    ä¸ĢåĮº
    -0.07
    riangle
    -0.07
    redicate
    -0.07
    POSITIVE LOGITS
     rate
    0.08
    -rate
    0.07
     rates
    0.07
    çİĩ
    0.06
    esh
    0.06
    sap
    0.06
    yme
    0.06
    /inc
    0.06
    resher
    0.06
    cko
    0.06
    Activations Density 0.007%

    No Known Activations