© 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. 84872
    Prev
    Next
    INDEX
    Explanations

    statements concerning healthcare and community-related issues

    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
    eson
    -0.08
    .swagger
    -0.08
    à¸Ńะ
    -0.07
    iero
    -0.07
     Relative
    -0.07
    ä»Ķ
    -0.07
    uggy
    -0.07
    .Relative
    -0.07
    QRST
    -0.07
    á¹
    -0.07
    POSITIVE LOGITS
     community
    0.08
     valley
    0.08
     locally
    0.08
     access
    0.08
     availability
    0.07
     convenient
    0.07
     local
    0.07
     accessibility
    0.07
     convenience
    0.07
     residents
    0.07
    Activations Density 0.035%

    No Known Activations