© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80246
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations and compliance related to various substances and practices

    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
    prak
    -0.07
    vertis
    -0.06
    traction
    -0.06
     Gerard
    -0.06
    ansen
    -0.06
    utow
    -0.06
     âĢ¦↵
    -0.06
    ior
    -0.06
    ooter
    -0.06
    ÏĦοκ
    -0.06
    POSITIVE LOGITS
     applicable
    0.10
     laws
    0.09
    /reg
    0.09
    laws
    0.09
     Laws
    0.09
    /legal
    0.08
     relevant
    0.08
     regulators
    0.08
    relevant
    0.07
    licable
    0.07
    Activations Density 0.025%

    No Known Activations