© 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. 90751
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to particle decay processes

    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
    æł·çļĦ
    -0.08
    ATAB
    -0.07
    yo
    -0.06
    iyah
    -0.06
    ething
    -0.06
    몰
    -0.06
    iddi
    -0.06
    zo
    -0.06
    UNET
    -0.06
    íĻĶ를
    -0.06
    POSITIVE LOGITS
    ÂŃing
    0.08
    otron
    0.08
    rate
    0.08
    RATE
    0.07
    /rest
    0.07
    adero
    0.07
    itest
    0.07
    ogue
    0.07
    ORA
    0.07
    ed
    0.07
    Activations Density 0.013%

    No Known Activations