© 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. 16884
    Prev
    Next
    INDEX
    Explanations

    references to dedications and tributes in various contexts

    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
    åŃĿ
    -0.08
     nackte
    -0.07
    fos
    -0.07
    á»ijt
    -0.07
    _RG
    -0.07
     __("
    -0.07
    اÙĪÙĬ
    -0.07
    /Runtime
    -0.06
    uilt
    -0.06
    .bot
    -0.06
    POSITIVE LOGITS
    ogens
    0.06
     marty
    0.06
    ecure
    0.06
     victims
    0.06
     old
    0.06
    erox
    0.06
     those
    0.06
     Metrics
    0.06
     wh
    0.06
    argar
    0.06
    Activations Density 0.015%

    No Known Activations