© 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. 131030
    Prev
    Next
    INDEX
    Explanations

    references to discounts and sales on Microsoft Surface devices

    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
    //{{
    -0.09
    iani
    -0.09
    arine
    -0.08
    #__
    -0.08
    ÑĤÑİ
    -0.08
    té
    -0.08
    ibri
    -0.07
     ÑĦоÑĢ
    -0.07
    <typeof
    -0.07
    PÅĻÃŃ
    -0.07
    POSITIVE LOGITS
    998
    0.07
     orders
    0.06
    orders
    0.06
     editorial
    0.06
     spraw
    0.06
    be
    0.06
     Bee
    0.06
     ìłĢ
    0.05
    996
    0.05
     Rew
    0.05
    Activations Density 0.004%

    No Known Activations