© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26631
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in code, likely focusing on programming syntax and variable declarations

    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
     migrationBuilder
    -0.08
    æł·çļĦ
    -0.07
    esModule
    -0.07
     behalf
    -0.07
    (es
    -0.07
    aul
    -0.07
    gue
    -0.07
    -do
    -0.07
    /do
    -0.07
    opp
    -0.06
    POSITIVE LOGITS
    aÄŁa
    0.07
    maal
    0.07
    ãģĤãģ£ãģŁ
    0.07
    omore
    0.07
    ī
    0.06
    ovable
    0.06
    oret
    0.06
    959
    0.06
    83
    0.06
    جاÙĨ
    0.06
    Activations Density 0.105%

    No Known Activations