© 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. 90541
    Prev
    Next
    INDEX
    Explanations

    references to specific events or actions

    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
    wig
    -0.06
    alle
    -0.06
    оки
    -0.06
    ÏĦή
    -0.06
    endor
    -0.06
    wick
    -0.06
     Pagination
    -0.06
    971
    -0.06
     lead
    -0.06
     jadx
    -0.06
    POSITIVE LOGITS
    udder
    0.07
    ếp
    0.07
     sinc
    0.07
    istrat
    0.06
     Vote
    0.06
     karÅŁ
    0.06
    еÑĢеж
    0.06
    NEWS
    0.06
    Æ°á»Ŀng
    0.06
    eding
    0.06
    Activations Density 0.015%

    No Known Activations