© 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. 93597
    Prev
    Next
    INDEX
    Explanations

    references to sleep functions and delays in programming code

    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
    /column
    -0.06
    mph
    -0.06
    nown
    -0.06
    therapy
    -0.06
    ล
    -0.05
    croll
    -0.05
    etype
    -0.05
    бÑĥ
    -0.05
     dziew
    -0.05
    ÑĸÑİ
    -0.05
    POSITIVE LOGITS
    ť
    0.07
    skirts
    0.07
    chia
    0.07
    éļ
    0.06
    722
    0.06
     underst
    0.06
     geçen
    0.06
    ëıĻìķĪ
    0.06
    ÙĪÛĮس
    0.06
     tact
    0.06
    Activations Density 0.009%

    No Known Activations