Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5560
    Prev
    Next
    INDEX
    Explanations

    expressions related to international relations and geopolitical strategies

    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
     âĹİ
    -0.07
    æk
    -0.07
    çĭ
    -0.07
    forman
    -0.06
    zia
    -0.06
    orang
    -0.06
    aso
    -0.06
    endor
    -0.06
     ìĿ´ìĸ´
    -0.06
    746
    -0.06
    POSITIVE LOGITS
    èį
    0.07
    resse
    0.07
    Indeed
    0.06
    Tier
    0.06
    tier
    0.06
     opr
    0.06
    ãģıãĤĵ
    0.06
    inde
    0.06
    verse
    0.06
    iddle
    0.06
    Activations Density 0.000%

    No Known Activations