© 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. 58245
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and compliance in a legal context

    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
    azen
    -0.07
    cape
    -0.07
     Rent
    -0.06
    laÄį
    -0.06
    iams
    -0.06
     ات
    -0.06
    mium
    -0.06
    riad
    -0.06
    лоÑĢ
    -0.06
    .pnl
    -0.06
    POSITIVE LOGITS
    cÃŃ
    0.08
    ToLocal
    0.07
    .RegisterType
    0.07
    ãĥªãĥ³ãĤ°
    0.07
    ivot
    0.06
    oplayer
    0.06
    .sec
    0.06
    omanip
    0.06
    .hist
    0.06
    icken
    0.06
    Activations Density 0.003%

    No Known Activations