© 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. 71092
    Prev
    Next
    INDEX
    Explanations

    elements related to events and tickets in a marketing context

    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
    %E
    -0.07
    lest
    -0.06
    asa
    -0.06
    ENTA
    -0.06
    AZY
    -0.06
    ago
    -0.06
    ÐŁÐļ
    -0.06
    asse
    -0.06
    ['__
    -0.06
    821
    -0.06
    POSITIVE LOGITS
    åŃIJãģ¯
    0.10
     will
    0.09
     may
    0.09
     can
    0.08
     are
    0.08
     is
    0.07
    ãģ¯
    0.07
     ãģ¯
    0.07
    ìĿĢ
    0.06
     adalah
    0.06
    Activations Density 0.035%

    No Known Activations