© 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. 130076
    Prev
    Next
    INDEX
    Explanations

    character sets and their usage in written languages

    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
    aston
    -0.07
    ishly
    -0.07
    ษ
    -0.06
     crunch
    -0.06
    /utility
    -0.06
    atical
    -0.06
     clo
    -0.06
    à¸Ńà¸ļ
    -0.06
    kj
    -0.06
     eller
    -0.06
    POSITIVE LOGITS
    ÏĤ
    0.08
    ï¸ı
    0.07
    XL
    0.07
     pornografia
    0.07
    rias
    0.07
    ç²
    0.07
    mue
    0.06
    ãĤĪãģ³
    0.06
    ARAM
    0.06
    _pdata
    0.06
    Activations Density 0.015%

    No Known Activations