© 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. 83798
    Prev
    Next
    INDEX
    Explanations

    references to flood-related issues and insurance

    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
    cen
    -0.07
    zelf
    -0.07
    ×ķ
    -0.07
     oui
    -0.07
     Aires
    -0.06
    /apt
    -0.06
    CODE
    -0.06
    lices
    -0.06
    ÙĬج
    -0.06
    ë§ī
    -0.06
    POSITIVE LOGITS
    plain
    0.08
    edImage
    0.07
    acco
    0.07
    ding
    0.07
    raph
    0.07
    atori
    0.07
    pl
    0.07
    meter
    0.07
     FM
    0.06
    esin
    0.06
    Activations Density 0.003%

    No Known Activations