© 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. 119865
    Prev
    Next
    INDEX
    Explanations

    prepositions that indicate relationships or connections

    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
    our
    -0.06
    exampleInputEmail
    -0.06
    duct
    -0.06
     the
    -0.06
    king
    -0.06
    olon
    -0.06
    exampleInput
    -0.06
    kla
    -0.06
    fav
    -0.06
     st
    -0.05
    POSITIVE LOGITS
    essor
    0.08
    iciálnÃŃ
    0.08
    865
    0.07
    _Off
    0.07
    icial
    0.07
    soever
    0.07
    ffset
    0.07
    -course
    0.07
    CJK
    0.07
     sorts
    0.07
    Activations Density 0.030%

    No Known Activations