© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    references to code execution and structural elements of programming

    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
    $MESS
    -0.08
    REDIENT
    -0.08
     Ùĩا
    -0.07
     sof
    -0.07
    ↵↵
    -0.07
    SetBranch
    -0.06
    using
    -0.06
    ÏħÏĥ
    -0.06
    lparr
    -0.06
    viron
    -0.06
    POSITIVE LOGITS
    rient
    0.07
    mue
    0.06
    ä»ĭ
    0.06
    oÅĪ
    0.06
    ÙĬاÙĨ
    0.06
     conclus
    0.06
    erli
    0.06
    mani
    0.06
    -ÑĤо
    0.06
    äºĭ
    0.05
    Activations Density 0.274%

    No Known Activations