© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84417
    Prev
    Next
    INDEX
    Explanations

    references to luxury goods and services

    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
     unleash
    -0.06
    ifen
    -0.06
    ampo
    -0.06
     thrift
    -0.06
     lowes
    -0.06
     frem
    -0.05
     unleashed
    -0.05
    beer
    -0.05
    AIT
    -0.05
     Erd
    -0.05
    POSITIVE LOGITS
     luxury
    0.10
     Luxury
    0.09
    conc
    0.09
     Clients
    0.09
     Private
    0.09
    CLIENT
    0.08
     Wealth
    0.08
     Client
    0.08
     conc
    0.08
     clients
    0.08
    Activations Density 0.124%

    No Known Activations