© 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. 17-LLAMASCOPE-RES-131K
    11. 77730
    Prev
    Next
    INDEX
    Explanations

    references to geometric shapes and their properties in a programming context

    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
    .MixedReality
    -0.08
    ocre
    -0.08
    ults
    -0.07
    еÑĢеж
    -0.07
    peria
    -0.07
    utta
    -0.07
    ï¼ļ"
    -0.07
    presso
    -0.07
    .nih
    -0.07
    /**↵↵
    -0.07
    POSITIVE LOGITS
     Moments
    0.06
    amber
    0.06
    wart
    0.06
    zept
    0.06
    ikan
    0.06
    ihn
    0.06
    اذ
    0.06
    ترÛĮ
    0.06
    swer
    0.06
    Ñijн
    0.06
    Activations Density 0.008%

    No Known Activations