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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78537
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its involvement or influence in various contexts

    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
     ÄĮeská
    -0.08
    )::
    -0.07
    bild
    -0.07
    à¥Ģध
    -0.07
     kone
    -0.07
     rodin
    -0.07
     *,↵
    -0.06
     deÄŁerli
    -0.06
     lai
    -0.06
    .↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
     ‘
    0.07
    ?↵
    0.07
    raquo
    0.07
     UPDATED
    0.06
     ...)↵
    0.06
     '
    0.06
    !↵
    0.06
    nbsp
    0.06
    ãĢĭ↵
    0.06
    ings
    0.06
    Activations Density 0.026%

    No Known Activations