© 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. 15-LLAMASCOPE-RES-131K
    11. 88928
    Prev
    Next
    INDEX
    Explanations

    references to top services or products in various categories

    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
    iven
    -0.06
    lier
    -0.06
    finity
    -0.06
    orte
    -0.06
     either
    -0.06
    \
    -0.06
    omat
    -0.06
    odem
    -0.05
    ather
    -0.05
    burgh
    -0.05
    POSITIVE LOGITS
    #ac
    0.07
    anı
    0.07
     loa
    0.07
    à¸Ħรà¸ļ
    0.07
    quoise
    0.07
    ände
    0.07
    üny
    0.07
     ìĦľìļ¸íĬ¹ë³Ħìĭľ
    0.07
    _________________↵↵
    0.07
     Quit
    0.07
    Activations Density 0.055%

    No Known Activations