© 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. 29658
    Prev
    Next
    INDEX
    Explanations

    references to countries, governments, and prominent figures related to international affairs

    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
    (æĹ¥
    -0.07
    Č↵
    -0.07
    Ups
    -0.06
    idar
    -0.06
     pros
    -0.06
    ész
    -0.06
    913
    -0.06
    abant
    -0.06
    foreground
    -0.06
    iper
    -0.06
    POSITIVE LOGITS
     Sparks
    0.07
    imson
    0.07
    DITION
    0.06
    allah
    0.06
    еÑĤÑĮ
    0.06
    íijľ
    0.06
    uely
    0.06
    ãģ¾ãģ¾
    0.06
    ATUS
    0.06
    ilip
    0.06
    Activations Density 0.060%

    No Known Activations