© 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. 88957
    Prev
    Next
    INDEX
    Explanations

    elements of architecture and artistic features in descriptions

    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
    ucha
    -0.07
    enade
    -0.06
    ongyang
    -0.06
    ARSER
    -0.06
     voks
    -0.06
    絶
    -0.06
    fo
    -0.06
     tan
    -0.06
    irie
    -0.06
    clr
    -0.06
    POSITIVE LOGITS
    елик
    0.07
    سÙĪ
    0.07
    pedia
    0.07
    FAULT
    0.07
     Insider
    0.07
    markt
    0.06
    UDO
    0.06
     intéress
    0.06
    [:]
    0.06
    .showMessage
    0.06
    Activations Density 0.010%

    No Known Activations