© 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. 106071
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes in business commission structures

    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
    berger
    -0.06
     Edgar
    -0.06
    ãĥĨãĤ£
    -0.06
    برÛĮ
    -0.06
    doc
    -0.06
    तम
    -0.06
    DOC
    -0.06
    589
    -0.06
    iom
    -0.06
     proven
    -0.06
    POSITIVE LOGITS
     booking
    0.08
     Kemp
    0.08
    otel
    0.08
     Marriott
    0.08
     hotel
    0.08
     Hotels
    0.08
    éħĴåºĹ
    0.08
     bookings
    0.07
    ammed
    0.07
     Booking
    0.07
    Activations Density 0.008%

    No Known Activations