© 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. 15433
    Prev
    Next
    INDEX
    Explanations

    programming-related class definitions and descriptions

    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
    /Foundation
    -0.07
    ViewControllerAnimated
    -0.06
    dds
    -0.06
    å¸ĸ
    -0.06
     Align
    -0.06
    uiten
    -0.06
    arlo
    -0.06
    êu
    -0.06
    uche
    -0.06
    ÑĢаÑģÑĤ
    -0.06
    POSITIVE LOGITS
    emek
    0.06
    grounds
    0.06
    ä¹İ
    0.06
    گاÙĩ
    0.06
    393
    0.06
    cken
    0.06
    çī
    0.06
    евиÑĩ
    0.06
    _typ
    0.06
    ysi
    0.05
    Activations Density 0.000%

    No Known Activations