© 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. 93742
    Prev
    Next
    INDEX
    Explanations

    phrases indicating professionalism and service in a business context

    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
     honour
    -0.08
     US
    -0.07
     neighbourhood
    -0.07
     labour
    -0.07
     fibre
    -0.07
     mission
    -0.07
     scept
    -0.07
     armour
    -0.06
    uell
    -0.06
     programme
    -0.06
    POSITIVE LOGITS
     Westbrook
    0.08
    (æĹ¥
    0.08
    SSIP
    0.08
    ÅĻeb
    0.08
    بÙĬرة
    0.08
    .viewDidLoad
    0.07
     quotations
    0.07
     ìĿ´ëŁ¬íķľ
    0.07
    å¾
    0.07
    turnstile
    0.07
    Activations Density 0.542%

    No Known Activations