© 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. 107317
    Prev
    Next
    INDEX
    Explanations

    phrases related to online registration and websites

    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
     Binder
    -0.06
    hton
    -0.06
    renom
    -0.06
    igham
    -0.05
    awn
    -0.05
    rypt
    -0.05
    bu
    -0.05
    -0.05
    ovo
    -0.05
    mental
    -0.05
    POSITIVE LOGITS
     smr
    0.07
    é¡į
    0.07
    itz
    0.07
    νÏī
    0.07
     Äijảo
    0.07
    اÙĬت
    0.07
    íĸ¥
    0.07
    ãĥªãĤ¢
    0.07
    elog
    0.07
    ÑģилÑĮ
    0.07
    Activations Density 0.001%

    No Known Activations