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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57879
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory oversight and food safety

    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
     leadership
    -0.06
    osoph
    -0.06
    вай
    -0.06
    áng
    -0.06
    ulty
    -0.06
    oS
    -0.06
     optics
    -0.06
    quota
    -0.06
     Záp
    -0.06
    ä¼Ŀ
    -0.06
    POSITIVE LOGITS
     Auditor
    0.08
     auditor
    0.07
     report
    0.07
     audit
    0.07
    report
    0.07
    onu
    0.07
     Report
    0.07
     аÑĥд
    0.07
    IPA
    0.07
     Fraud
    0.07
    Activations Density 0.070%

    No Known Activations