© 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. 27913
    Prev
    Next
    INDEX
    Explanations

    file path and directory-related operations in programming contexts

    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
    macen
    -0.09
    Äįást
    -0.08
    вий
    -0.07
     NÄĽk
    -0.07
    ibly
    -0.07
    ÑģилÑĮ
    -0.07
    tainment
    -0.07
    она
    -0.07
    podob
    -0.07
    .MixedReality
    -0.07
    POSITIVE LOGITS
    ned
    0.08
     heck
    0.07
    azo
    0.06
    azers
    0.06
     hell
    0.06
    abs
    0.06
    erva
    0.05
    mas
    0.05
    ined
    0.05
     Hell
    0.05
    Activations Density 0.001%

    No Known Activations