© 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. 40796
    Prev
    Next
    INDEX
    Explanations

    references to premium amenities or services in hospitality settings

    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
    åĽ
    -0.06
     blocks
    -0.05
    Handle
    -0.05
    ÑĢаг
    -0.05
    ainless
    -0.05
     pron
    -0.05
     Kho
    -0.05
    Modified
    -0.05
    rama
    -0.05
     domain
    -0.05
    POSITIVE LOGITS
    ç¿Ķ
    0.08
     lounge
    0.07
    ounge
    0.07
     Suites
    0.07
     Desk
    0.07
    herits
    0.07
    frauen
    0.07
    çĴĥ
    0.07
     Lounge
    0.07
    ãģĵãģ¡ãĤī
    0.07
    Activations Density 0.003%

    No Known Activations