© 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 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. 17-LLAMASCOPE-RES-131K
    11. 106148
    Prev
    Next
    INDEX
    Explanations

    comments and annotations within programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comment markers in programming code - either "*" within multi-line documentation blocks or "//" for single-line comments.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ÑĢеп
    -0.07
    ãĥĥãĥģ
    -0.07
    werp
    -0.07
     èĩªåĬ¨çĶŁæĪIJ
    -0.07
    ecom
    -0.07
    arah
    -0.06
    ılım
    -0.06
    YTE
    -0.06
    æĹ¥ãģ«
    -0.06
    ات
    -0.06
    POSITIVE LOGITS
    @qq
    0.07
    rien
    0.07
    tron
    0.06
    amil
    0.06
    olec
    0.06
     λÏĮγ
    0.06
    ONGL
    0.06
    à¸ĩà¸Ħ
    0.05
    kt
    0.05
    ksi
    0.05
    Activations Density 0.038%

    No Known Activations