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

    Neuronpedia

    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. 125053
    Prev
    Next
    INDEX
    Explanations

    phrases indicating communication or indication of information

    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
    .voice
    -0.07
    à¸ķะ
    -0.07
    affen
    -0.07
    _PATCH
    -0.07
    .Formatting
    -0.07
    ียà¸Ķ
    -0.07
    ียม
    -0.07
    umer
    -0.06
    _TD
    -0.06
    riot
    -0.06
    POSITIVE LOGITS
    atab
    0.07
     change
    0.07
    ize
    0.07
     changes
    0.07
     doom
    0.06
     that
    0.06
    aty
    0.06
    izes
    0.06
    atti
    0.06
    uture
    0.06
    Activations Density 0.009%

    No Known Activations