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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5441
    Prev
    Next
    INDEX
    Explanations

    words related to productivity and operational efficiency in a business context

    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
    fil
    -0.06
     iter
    -0.06
    ph
    -0.06
    wm
    -0.06
     proportion
    -0.06
    ikler
    -0.06
     correspond
    -0.06
     global
    -0.05
    [
    -0.05
    NY
    -0.05
    POSITIVE LOGITS
     Profit
    0.09
    Profit
    0.08
    Schedulers
    0.07
    Owner
    0.07
     profitable
    0.07
    zı
    0.07
     profit
    0.07
     Owner
    0.07
    Parts
    0.07
     profitability
    0.07
    Activations Density 0.001%

    No Known Activations