© 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. 53974
    Prev
    Next
    INDEX
    Explanations

    phrases related to health studies and clinical outcomes

    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
    zan
    -0.06
    Ñĥг
    -0.06
    uf
    -0.06
     works
    -0.06
     Diamonds
    -0.06
    еком
    -0.05
    works
    -0.05
     warning
    -0.05
    ingen
    -0.05
    اÙĤ
    -0.05
    POSITIVE LOGITS
    ropol
    0.07
    ιακ
    0.06
    ymm
    0.06
    acÃŃm
    0.06
    ghan
    0.06
    plen
    0.06
    ildo
    0.06
    leaflet
    0.06
     Gilles
    0.06
    YNC
    0.06
    Activations Density 0.000%

    No Known Activations