Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57346
    Prev
    Next
    INDEX
    Explanations

    phrases related to the provision of services and assistance

    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
    oulos
    -0.08
    ÑĤивного
    -0.06
    043
    -0.06
    iets
    -0.06
    ÙĬØ·
    -0.06
    ãĤ´ãĥª
    -0.06
    /big
    -0.06
    abbage
    -0.06
    emen
    -0.06
    ráf
    -0.06
    POSITIVE LOGITS
     services
    0.15
    services
    0.12
     ÑĥÑģлÑĥг
    0.12
    -services
    0.12
    ervices
    0.11
    Services
    0.11
    _services
    0.11
     Services
    0.11
    /services
    0.11
     serviços
    0.10
    Activations Density 0.029%

    No Known Activations