© 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. 61538
    Prev
    Next
    INDEX
    Explanations

    references to lighting and flash features in photography

    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
    gre
    -0.06
     gre
    -0.06
     lubric
    -0.06
    缮ãģ®
    -0.06
    Tracking
    -0.06
     rolling
    -0.06
     inputData
    -0.06
    .getInputStream
    -0.06
    rolling
    -0.06
     tiener
    -0.06
    POSITIVE LOGITS
    issy
    0.07
    edis
    0.07
    avity
    0.07
     discre
    0.06
    ump
    0.06
    ledi
    0.06
     flash
    0.06
     cand
    0.06
    Å¡ov
    0.06
     distance
    0.06
    Activations Density 0.002%

    No Known Activations