Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43492
    Prev
    Next
    INDEX
    Explanations

    terms related to the National Health Service (NHS) and health care concepts

    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
     Consumers
    -0.07
     Customers
    -0.06
    اء
    -0.06
     merchants
    -0.06
     Merch
    -0.06
    isk
    -0.06
     Teens
    -0.06
    inx
    -0.06
     businessmen
    -0.06
    xaa
    -0.06
    POSITIVE LOGITS
     workforce
    0.13
     staffing
    0.12
     nursing
    0.10
     RC
    0.10
     nurse
    0.10
     staff
    0.10
     recruitment
    0.10
     trusts
    0.10
     Nursing
    0.10
     nurses
    0.10
    Activations Density 0.009%

    No Known Activations