© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3240
    Prev
    Next
    INDEX
    Explanations

    references to groups of people or demographics, particularly in contexts of migration or social issues

    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
     moc
    -0.10
    ì´
    -0.08
    oca
    -0.07
    ầy
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    arme
    -0.07
    .oc
    -0.07
     Ùħب
    -0.07
    ообÑĢаз
    -0.07
    ickt
    -0.07
    POSITIVE LOGITS
     among
    0.09
     amongst
    0.09
    among
    0.08
     Among
    0.07
     accounted
    0.07
    Among
    0.06
     Angel
    0.06
    thic
    0.06
     account
    0.06
     ÑģÑĢеди
    0.06
    Activations Density 0.083%

    No Known Activations