© 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. 108513
    Prev
    Next
    INDEX
    Explanations

    terms related to government regulation and oversight

    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
    ếp
    -0.09
    oby
    -0.08
    inki
    -0.07
    -0.07
    ings
    -0.07
    سÙĪب
    -0.07
    /sn
    -0.07
    że
    -0.07
    924
    -0.07
    /read
    -0.07
    POSITIVE LOGITS
    /reg
    0.10
     же
    0.07
    ised
    0.07
    haus
    0.07
    ncia
    0.07
    ally
    0.07
    .LookAndFeel
    0.07
     dÄ±ÅŁÄ±
    0.07
    lox
    0.07
    aden
    0.07
    Activations Density 0.017%

    No Known Activations