© 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. 78115
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal expertise and professional experience

    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
    Å¡ek
    -0.08
     McMaster
    -0.07
    anou
    -0.07
    HEMA
    -0.07
    itez
    -0.07
    icerca
    -0.07
    kker
    -0.06
    imbus
    -0.06
    ommen
    -0.06
    Ñĩи
    -0.06
    POSITIVE LOGITS
    edin
    0.07
    utoff
    0.06
    este
    0.06
    icket
    0.06
    Clients
    0.06
    363
    0.06
    gh
    0.06
     Mob
    0.06
    icum
    0.06
    ë
    0.06
    Activations Density 0.003%

    No Known Activations