© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    significant historical events and dates

    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
    emer
    -0.06
    trieve
    -0.06
    .opensource
    -0.06
    ÑĢаг
    -0.06
    çŃ
    -0.06
    orent
    -0.06
    æĺŁ
    -0.06
    ereum
    -0.06
     shuttle
    -0.06
    ritel
    -0.06
    POSITIVE LOGITS
     famously
    0.07
     historic
    0.07
    ún
    0.07
     iconic
    0.06
     Classic
    0.06
    symbol
    0.06
    Fld
    0.06
    kuk
    0.06
    mile
    0.06
    olv
    0.06
    Activations Density 0.015%

    No Known Activations