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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129151
    Prev
    Next
    INDEX
    Explanations

    references to competition and rankings within sports events

    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
     mastur
    -0.07
     kostenlose
    -0.07
    .paper
    -0.07
     Kurum
    -0.07
     Verfüg
    -0.07
     kapit
    -0.07
     piger
    -0.07
    ipse
    -0.07
     Åŀubat
    -0.07
    анÑģи
    -0.07
    POSITIVE LOGITS
     top
    0.07
     saw
    0.06
     winner
    0.06
     whoever
    0.06
     completion
    0.06
     results
    0.06
     Edition
    0.06
     Whoever
    0.06
     imp
    0.06
     someone
    0.06
    Activations Density 0.053%

    No Known Activations