© 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. 27309
    Prev
    Next
    INDEX
    Explanations

    events or significant occurrences related to ceremonies or gatherings

    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
    ayer
    -0.09
    AYER
    -0.08
    enge
    -0.07
     initial
    -0.07
     unwanted
    -0.07
     first
    -0.06
     sometimes
    -0.06
    /pm
    -0.06
     grav
    -0.06
     later
    -0.06
    POSITIVE LOGITS
     ÛĮعÙĨÛĮ
    0.07
    ')['
    0.07
    LTR
    0.07
    eyin
    0.07
    ollider
    0.07
    _Last
    0.07
    ãģ£ãģ
    0.06
     å©
    0.06
    woke
    0.06
    ä¸į足
    0.06
    Activations Density 0.019%

    No Known Activations