© 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. 57743
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional services and teamwork

    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
    wig
    -0.07
    âĻª
    -0.07
    мов
    -0.07
    plevel
    -0.07
    pcf
    -0.07
    pus
    -0.07
     æĺ
    -0.07
    OnInit
    -0.07
    ÛĮدÛĮ
    -0.07
    виг
    -0.07
    POSITIVE LOGITS
     network
    0.07
     partner
    0.07
     Partner
    0.07
     vet
    0.06
     networks
    0.06
     whenever
    0.06
     partners
    0.06
     паÑĢÑĤ
    0.06
     Network
    0.06
    vet
    0.06
    Activations Density 0.011%

    No Known Activations