© 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. 29118
    Prev
    Next
    INDEX
    Explanations

    closing braces in programming code

    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
    ingo
    -0.07
    ocks
    -0.06
    _TRAN
    -0.06
    istine
    -0.06
    baum
    -0.06
    ystick
    -0.06
     Slut
    -0.06
    yme
    -0.06
    ร
    -0.06
    elsing
    -0.06
    POSITIVE LOGITS
    riday
    0.06
    azer
    0.06
    ze
    0.06
     worlds
    0.06
    tenant
    0.06
    zdy
    0.06
    ouden
    0.06
     Crown
    0.06
    ANNEL
    0.06
     nackte
    0.06
    Activations Density 0.002%

    No Known Activations