© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5982
    Prev
    Next
    INDEX
    Explanations

    terms related to medical testing and diagnostics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ÑģÑĤÑĮ
    -0.07
     ä¸ĢèĪ¬
    -0.07
    /respond
    -0.07
    ãģŁãĤģãģ®
    -0.07
    /manage
    -0.07
    .DefaultCellStyle
    -0.07
    ÑĪÑĤ
    -0.07
     yapıyor
    -0.07
     xxxx
    -0.07
    etÃŃ
    -0.07
    POSITIVE LOGITS
     analysis
    0.11
     studies
    0.10
     evidence
    0.09
     study
    0.09
    -based
    0.09
     data
    0.08
     results
    0.08
     analyses
    0.08
    analysis
    0.08
    -Based
    0.07
    Activations Density 0.049%

    No Known Activations