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. 44421
    Prev
    Next
    INDEX
    Explanations

    financial implications and operational decisions related to business entities

    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
    letcher
    -0.06
    oreach
    -0.06
    oller
    -0.06
     Hollywood
    -0.06
    »
    -0.06
     flavors
    -0.05
    ellar
    -0.05
    fol
    -0.05
    ologic
    -0.05
     Investments
    -0.05
    POSITIVE LOGITS
     contract
    0.10
     labour
    0.09
     casual
    0.09
     Casual
    0.09
     unions
    0.09
     salary
    0.09
     workers
    0.09
     contractual
    0.09
     salaries
    0.09
     regularization
    0.08
    Activations Density 0.006%

    No Known Activations