© 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. 27329
    Prev
    Next
    INDEX
    Explanations

    references to leadership programs and professional development initiatives

    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
    gni
    -0.07
    lug
    -0.07
    utex
    -0.07
    Åijs
    -0.07
    encent
    -0.07
    ç´
    -0.06
    ç°
    -0.06
    Äįin
    -0.06
    arn
    -0.06
    fold
    -0.06
    POSITIVE LOGITS
     leadership
    0.11
     Leadership
    0.11
    leaders
    0.09
    Leaders
    0.09
     Leader
    0.08
     Leaders
    0.08
     leader
    0.07
    ,eg
    0.07
    obl
    0.07
     Political
    0.07
    Activations Density 0.147%

    No Known Activations