© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71970
    Prev
    Next
    INDEX
    Explanations

    terms related to business and commerce activities

    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
    cheon
    -0.07
    ashi
    -0.06
    ìĿ´ìŀIJ
    -0.06
    udem
    -0.06
    tol
    -0.06
    .erb
    -0.06
    oug
    -0.06
    uger
    -0.06
    ear
    -0.06
    agged
    -0.06
    POSITIVE LOGITS
     often
    0.12
    often
    0.11
     because
    0.10
     either
    0.10
    because
    0.09
     Often
    0.09
     afin
    0.09
    Often
    0.09
    ometimes
    0.09
     sometimes
    0.09
    Activations Density 0.053%

    No Known Activations