© 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. 15-LLAMASCOPE-RES-131K
    11. 62064
    Prev
    Next
    INDEX
    Explanations

    expressions indicating ongoing debates and conflicting opinions

    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
    owski
    -0.07
     Gee
    -0.06
    @email
    -0.06
     Critics
    -0.06
    SystemService
    -0.06
     Verde
    -0.06
    HandlerContext
    -0.06
    ennie
    -0.06
    ään
    -0.06
    Reviewer
    -0.06
    POSITIVE LOGITS
     express
    0.07
    ï¼ł
    0.07
    ãĢ
    0.07
    izon
    0.07
    elize
    0.07
    ÑĢив
    0.07
     among
    0.06
    /groups
    0.06
    è¼
    0.06
     amongst
    0.06
    Activations Density 0.026%

    No Known Activations