© 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. 15490
    Prev
    Next
    INDEX
    Explanations

    references to food safety and regulatory 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
    levision
    -0.09
    KIT
    -0.07
     chamber
    -0.07
    kit
    -0.07
     Chamber
    -0.07
     stained
    -0.07
    -vars
    -0.07
    олÑĮно
    -0.06
    ráf
    -0.06
     Detective
    -0.06
    POSITIVE LOGITS
    .nih
    0.08
     Federal
    0.07
     division
    0.07
     Division
    0.07
     federal
    0.07
     Office
    0.06
    Federal
    0.06
    cision
    0.06
    ushima
    0.06
     Cục
    0.06
    Activations Density 0.039%

    No Known Activations