© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    syntax structures and programming constructs within 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
    ÏģοÏħ
    -0.07
    ãģ£ãģ¨
    -0.07
     Op
    -0.07
    ModuleName
    -0.07
    adal
    -0.07
    ëł¹
    -0.07
    ÃĹ↵↵
    -0.07
    //---------------------------------------------------------------------------↵↵
    -0.07
    ué
    -0.07
    bert
    -0.07
    POSITIVE LOGITS
    164
    0.07
    heet
    0.06
    abble
    0.06
    ha
    0.06
    ware
    0.06
    å®Ĺ
    0.06
    163
    0.06
    haft
    0.06
    angu
    0.06
    åĸ
    0.06
    Activations Density 0.141%

    No Known Activations