© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106215
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions or locations, particularly universities and colleges

    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
     Stam
    -0.07
    ague
    -0.06
    oyer
    -0.06
    iani
    -0.06
    mey
    -0.06
    olla
    -0.06
    kip
    -0.06
    á»ĭnh
    -0.06
    ela
    -0.06
    kiego
    -0.06
    POSITIVE LOGITS
    esco
    0.07
    lez
    0.07
    won
    0.06
    _idle
    0.06
    swire
    0.06
    -REAL
    0.06
    _rng
    0.06
    ?>č↵
    0.06
    -toggler
    0.06
    ÑĢив
    0.05
    Activations Density 0.001%

    No Known Activations