© 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. 56036
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols, particularly those used in listings and prices

    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
    \b
    -0.06
    avo
    -0.06
    oji
    -0.06
    ért
    -0.06
    ุà¸ķร
    -0.05
     Catal
    -0.05
     apl
    -0.05
    ิà¸ĩห
    -0.05
     Rica
    -0.05
    CJK
    -0.05
    POSITIVE LOGITS
    Overview
    0.09
     Overview
    0.08
     overview
    0.08
     ÚĨÚ¯ÙĪÙĨÙĩ
    0.07
     Importance
    0.07
    ovat
    0.07
     why
    0.07
    overview
    0.07
    tip
    0.07
     hvordan
    0.07
    Activations Density 0.041%

    No Known Activations