© 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. 84064
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and the judicial process

    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
    quil
    -0.07
    itler
    -0.06
     ucwords
    -0.06
    \Console
    -0.06
    é±
    -0.06
    -fontawesome
    -0.06
    /backend
    -0.06
    prene
    -0.06
    é³
    -0.06
    ald
    -0.06
    POSITIVE LOGITS
    _argument
    0.07
     argument
    0.07
     presentation
    0.07
    argument
    0.07
     PowerPoint
    0.07
    vae
    0.07
    æĸ¹
    0.06
     Presentation
    0.06
    ERY
    0.06
    rief
    0.06
    Activations Density 0.015%

    No Known Activations