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

    Neuronpedia

    Jacobian LensNEW
    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. 29435
    Prev
    Next
    INDEX
    Explanations

    the term "service" and its various forms, indicating references to services provided or offered

    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
    ly
    -0.07
     acting
    -0.06
     Exercises
    -0.06
    481
    -0.06
     KeyValue
    -0.06
    iker
    -0.06
    tee
    -0.06
    ness
    -0.06
    éo
    -0.05
    eket
    -0.05
    POSITIVE LOGITS
    (Service
    0.09
    .GetService
    0.09
     Render
    0.09
    (service
    0.09
    /service
    0.08
    able
    0.08
    istrovstvÃŃ
    0.08
    ability
    0.08
    ruba
    0.07
     service
    0.07
    Activations Density 0.029%

    No Known Activations