© 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. 118109
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relationships or conditions

    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
    à¥Ģड
    -0.06
    essages
    -0.06
     (?
    -0.06
    atte
    -0.06
    ¡
    -0.06
     tremend
    -0.05
    opus
    -0.05
    gin
    -0.05
    ocus
    -0.05
     Ron
    -0.05
    POSITIVE LOGITS
     how
    0.14
     why
    0.13
     How
    0.10
    how
    0.10
    /how
    0.10
     what
    0.10
    -how
    0.10
    /or
    0.10
    How
    0.10
     Ø¢ÛĮا
    0.09
    Activations Density 0.013%

    No Known Activations