© 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. 87392
    Prev
    Next
    INDEX
    Explanations

    terms related to the pharmaceutical industry and women's health initiatives

    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
    éijij
    -0.07
    ongyang
    -0.07
     UIF
    -0.07
    zeich
    -0.07
    pNet
    -0.06
    grese
    -0.06
     Gap
    -0.06
    nické
    -0.06
    iciel
    -0.06
    utschein
    -0.06
    POSITIVE LOGITS
     drug
    0.08
     Lilly
    0.07
    icals
    0.07
     drugs
    0.07
    product
    0.07
     medicines
    0.07
     product
    0.06
     blockbuster
    0.06
     therapeutic
    0.06
    ingredient
    0.06
    Activations Density 0.025%

    No Known Activations