© 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. 83290
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals receiving services or assistance, particularly in health and customer contexts

    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
    ?action
    -0.06
     FactoryBot
    -0.06
    urn
    -0.06
    nya
    -0.06
    رسÛĮ
    -0.06
    sian
    -0.06
    arde
    -0.06
    å¼¥
    -0.06
    æ·»
    -0.06
    пиÑģ
    -0.05
    POSITIVE LOGITS
    /client
    0.08
    /member
    0.08
    aghan
    0.08
     satisfaction
    0.07
    hood
    0.07
    -centered
    0.07
    /customer
    0.07
    /student
    0.07
    friendly
    0.07
    agnet
    0.07
    Activations Density 0.033%

    No Known Activations