© 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. 77572
    Prev
    Next
    INDEX
    Explanations

    comparisons and expressions of change or development

    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
    asco
    -0.07
    .documentation
    -0.07
    ewan
    -0.07
    expo
    -0.06
    rosso
    -0.06
    CLOCKS
    -0.06
    ocos
    -0.06
    uelles
    -0.06
     Guys
    -0.06
    implify
    -0.06
    POSITIVE LOGITS
     today
    0.19
    today
    0.17
    ä»ĬæĹ¥
    0.15
     now
    0.15
     heute
    0.14
    _today
    0.14
    Today
    0.14
     Today
    0.14
    ä»Ĭ天
    0.14
     oggi
    0.13
    Activations Density 0.018%

    No Known Activations