© 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 EvalsExportsinterp-engineNEWAPI 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. 62662
    Prev
    Next
    INDEX
    Explanations

    boolean values and configuration-related keywords in 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
    ueur
    -0.06
    esson
    -0.06
    Ìģ
    -0.06
    анÑĤа
    -0.06
    ients
    -0.06
    _DEVICES
    -0.06
    erece
    -0.06
    ylvania
    -0.06
    ÄįÃŃ
    -0.06
    aille
    -0.06
    POSITIVE LOGITS
    =false
    0.06
    cheng
    0.06
     Fran
    0.06
    461
    0.06
     Schmidt
    0.06
    Fraction
    0.06
    /false
    0.06
    ÑģÑıÑĤ
    0.06
    MBProgressHUD
    0.06
     Dani
    0.06
    Activations Density 0.010%

    No Known Activations