© 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. 17-LLAMASCOPE-RES-131K
    11. 60137
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and components in 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
    ëĶĶìĭľ
    -0.09
    geç
    -0.08
    ãĤ«ãĥĨãĤ´ãĥª
    -0.07
     («
    -0.07
    éĺħ读次æķ°
    -0.07
    oÃłi
    -0.07
    stÃŃ
    -0.07
    /details
    -0.07
    toc
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    POSITIVE LOGITS
    ungs
    0.06
    regar
    0.06
     prepared
    0.06
    pora
    0.05
    alar
    0.05
    uya
    0.05
     proudly
    0.05
    eway
    0.05
    ester
    0.05
    ongo
    0.05
    Activations Density 0.016%

    No Known Activations