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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84055
    Prev
    Next
    INDEX
    Explanations

    phrases related to business interactions and service accommodations

    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
    alley
    -0.07
     cook
    -0.07
    abet
    -0.06
    -death
    -0.06
    bedo
    -0.06
    endon
    -0.06
    vak
    -0.06
    ars
    -0.06
     Cater
    -0.06
    astreet
    -0.06
    POSITIVE LOGITS
     Customer
    0.10
     customer
    0.10
    Customer
    0.09
    customer
    0.08
     customers
    0.08
     Customers
    0.08
     Kunden
    0.08
    rud
    0.08
    /customer
    0.07
    _customer
    0.07
    Activations Density 0.021%

    No Known Activations