© 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. 61691
    Prev
    Next
    INDEX
    Explanations

    statements about decision-making in response to changing circumstances

    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
    اضÛĮ
    -0.06
    è²
    -0.06
    lÃŃn
    -0.06
    ávÄĽ
    -0.06
     pan
    -0.06
    acÃŃ
    -0.06
    owied
    -0.06
    inki
    -0.06
    ignum
    -0.06
    angs
    -0.06
    POSITIVE LOGITS
    _CTL
    0.06
    _until
    0.06
     tô
    0.06
    ìļ
    0.06
     ÐľÐ¸ÐºÐ¾Ð»Ð°
    0.06
    apesh
    0.06
     situaci
    0.06
    ohon
    0.06
     absol
    0.06
     flexibility
    0.06
    Activations Density 0.003%

    No Known Activations