© 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. 86974
    Prev
    Next
    INDEX
    Explanations

    programming syntax or function definitions related to graphics and mathematical operations

    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
    оÑĢаз
    -0.07
    esso
    -0.07
    ÏĢά
    -0.07
    RefCount
    -0.06
    ield
    -0.06
     VÄĽ
    -0.06
    iked
    -0.06
    estre
    -0.06
    utzer
    -0.06
    ouce
    -0.06
    POSITIVE LOGITS
    uat
    0.07
     GURL
    0.07
    {:
    0.06
    chw
    0.06
    oa
    0.06
    apgolly
    0.06
     بÙĪابة
    0.06
     semiclass
    0.06
    acÃŃ
    0.06
    INU
    0.06
    Activations Density 0.008%

    No Known Activations