© 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. 89917
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses that indicate legal or formal actions

    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
    airo
    -0.07
    stru
    -0.06
    æĭĶ
    -0.06
    czy
    -0.06
    izio
    -0.06
    ãģĹãĤĩ
    -0.06
     kim
    -0.05
    à¸Ľà¸£à¸°à¸Īำ
    -0.05
     chim
    -0.05
     Peel
    -0.05
    POSITIVE LOGITS
    ündeki
    0.07
    æĸĻ
    0.07
    å»
    0.07
    _legal
    0.07
    ваннÑı
    0.07
    ller
    0.06
    ÃĦŸ
    0.06
    alace
    0.06
    Tre
    0.06
    Ñģклад
    0.06
    Activations Density 0.000%

    No Known Activations