© 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. 77164
    Prev
    Next
    INDEX
    Explanations

    phrases that convey uncertainty or specifications in quantity

    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
    ầm
    -0.07
    dea
    -0.07
    ÑĢей
    -0.06
    nton
    -0.06
    itas
    -0.06
    anki
    -0.06
    麼
    -0.06
    voke
    -0.06
    oldown
    -0.06
    ÑĭÑĤ
    -0.06
    POSITIVE LOGITS
     several
    0.07
    리ìĸ´
    0.06
     nothing
    0.06
    zik
    0.06
    yre
    0.06
    æĽ´å¤ļ
    0.06
     Ultra
    0.06
     sooner
    0.06
     two
    0.06
     even
    0.06
    Activations Density 0.013%

    No Known Activations