© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    phrases related to being a trusted choice in a specific industry or service

    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
    ITTE
    -0.07
    onis
    -0.07
    geries
    -0.07
    uling
    -0.07
    /latest
    -0.07
    акÑģим
    -0.07
    igar
    -0.07
    achuset
    -0.07
    .mob
    -0.06
    ESSAGE
    -0.06
    POSITIVE LOGITS
     choice
    0.09
     provider
    0.09
     providers
    0.08
     trusted
    0.07
     locally
    0.07
    provider
    0.07
     vendor
    0.07
    choice
    0.06
     local
    0.06
     company
    0.06
    Activations Density 0.020%

    No Known Activations