© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28679
    Prev
    Next
    INDEX
    Explanations

    references to business operations and the founding of companies

    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
    projects
    -0.07
    idency
    -0.07
    Projects
    -0.07
     ë§ŀ
    -0.07
     projects
    -0.06
     planners
    -0.06
    олÑİ
    -0.06
    tro
    -0.06
    peria
    -0.06
    оÑĢов
    -0.06
    POSITIVE LOGITS
     sales
    0.09
     patent
    0.09
     selling
    0.09
     sell
    0.09
    -selling
    0.09
     commercial
    0.08
     sold
    0.08
     company
    0.08
     sells
    0.08
    selling
    0.08
    Activations Density 0.005%

    No Known Activations