© 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. 76083
    Prev
    Next
    INDEX
    Explanations

    conditions and eligibility criteria for individuals, particularly related to disabilities and women’s health services

    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
    efore
    -0.07
    ób
    -0.07
    tere
    -0.07
    dden
    -0.07
    ì¤Ģ
    -0.07
    acam
    -0.07
    avr
    -0.06
     annunci
    -0.06
    apur
    -0.06
    iyi
    -0.06
    POSITIVE LOGITS
     household
    0.07
    ippi
    0.07
     sem
    0.06
    .orm
    0.06
     bon
    0.06
     ward
    0.06
     Meet
    0.06
    ÑģÑĤав
    0.06
     low
    0.06
     income
    0.06
    Activations Density 0.022%

    No Known Activations