© 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. 125503
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service and fulfillment

    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
    adol
    -0.07
    mada
    -0.07
    maal
    -0.06
     Wich
    -0.06
    orida
    -0.06
    onth
    -0.06
     Suche
    -0.06
    num
    -0.06
    quirrel
    -0.06
    lio
    -0.06
    POSITIVE LOGITS
    ynchronously
    0.07
     мов
    0.06
     templ
    0.06
    -Ass
    0.06
    .TryParse
    0.06
    pty
    0.06
    weit
    0.06
     мÑĸÑģÑĨÑĸ
    0.06
    templ
    0.06
    irez
    0.06
    Activations Density 0.006%

    No Known Activations