© 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. 40404
    Prev
    Next
    INDEX
    Explanations

    sequences with special characters, particularly underscores and periods

    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
    ubits
    -0.08
    erap
    -0.08
    CoreApplication
    -0.07
    ovsky
    -0.07
    alat
    -0.07
    )NULL
    -0.07
    asp
    -0.07
    edii
    -0.07
     deco
    -0.07
     Kad
    -0.07
    POSITIVE LOGITS
    é½IJ
    0.06
     Bobby
    0.06
    ayer
    0.06
     Meg
    0.06
     Trader
    0.06
    ZN
    0.06
    639
    0.06
    icket
    0.05
    513
    0.05
    621
    0.05
    Activations Density 0.012%

    No Known Activations