© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    keywords related to construction and product launches

    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
    udden
    -0.09
    ãģ°ãģĭãĤĬ
    -0.08
    .Compute
    -0.07
    aily
    -0.07
     Bugün
    -0.07
    today
    -0.07
    æĮ¯ãĤĬ
    -0.07
    ãģ¾ãģ¾
    -0.07
    ä»ĬæĹ¥
    -0.07
    ooter
    -0.07
    POSITIVE LOGITS
     next
    0.10
     year
    0.08
    rough
    0.07
     years
    0.07
     tahun
    0.07
    .year
    0.07
     Year
    0.06
    -next
    0.06
     Next
    0.06
     decade
    0.06
    Activations Density 0.024%

    No Known Activations