© 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. 75547
    Prev
    Next
    INDEX
    Explanations

    references to customer interactions and experiences 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
    (Constructor
    -0.08
    sÃŃ
    -0.07
    illo
    -0.07
    inez
    -0.07
    iddi
    -0.07
    ablo
    -0.07
    gow
    -0.07
    anio
    -0.07
    atik
    -0.06
     ÑģÑĤоÑı
    -0.06
    POSITIVE LOGITS
     interaction
    0.11
     interactions
    0.11
    interaction
    0.10
     Interaction
    0.10
    Interaction
    0.10
     contact
    0.08
     interact
    0.08
     interacting
    0.07
     interacts
    0.07
     touch
    0.07
    Activations Density 0.013%

    No Known Activations