© 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. 58441
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and legal disclaimers

    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
    urat
    -0.07
    uyo
    -0.06
    /fw
    -0.06
    ixon
    -0.06
     nghiá»ĩp
    -0.06
    ersen
    -0.06
    à¥Ĥà¤Ł
    -0.06
    stanov
    -0.06
    umo
    -0.06
    usp
    -0.06
    POSITIVE LOGITS
     complaint
    0.07
    licken
    0.06
     complaints
    0.06
    åij¨æľŁ
    0.06
     regulators
    0.06
    InstanceState
    0.06
     DMA
    0.06
    868
    0.06
     regulator
    0.06
    è½
    0.06
    Activations Density 0.001%

    No Known Activations