© 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. 5-LLAMASCOPE-RES-131K
    11. 125673
    Prev
    Next
    INDEX
    Explanations

    references to skin and skincare products

    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
    aal
    -0.07
    eur
    -0.06
    акон
    -0.06
    ogo
    -0.06
     State
    -0.06
    asco
    -0.06
    upakan
    -0.06
    sage
    -0.06
    оном
    -0.06
    곡
    -0.06
    POSITIVE LOGITS
    -thumbnails
    0.08
    SSERT
    0.07
    hattan
    0.07
    _Cmd
    0.07
    arm
    0.07
    arrera
    0.06
     ÐĴики
    0.06
    OptionPane
    0.06
    -uppercase
    0.06
    ÑģÑĤÑĭ
    0.06
    Activations Density 0.004%

    No Known Activations