© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129885
    Prev
    Next
    INDEX
    Explanations

    concerns related to personal data protection and breaches in healthcare data

    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
    kı
    -0.07
    èħ¹
    -0.06
    ]âĢı
    -0.06
     round
    -0.06
    616
    -0.06
    Ðĩ
    -0.06
    Ì
    -0.06
    fty
    -0.06
    OTA
    -0.06
    701
    -0.06
    POSITIVE LOGITS
     data
    0.11
    æķ°æį®
    0.10
    -data
    0.09
    data
    0.09
    ãĥĩãĥ¼ãĤ¿
    0.09
    _data
    0.09
     collected
    0.09
     Data
    0.09
     information
    0.08
     initData
    0.08
    Activations Density 0.093%

    No Known Activations