© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78872
    Prev
    Next
    INDEX
    Explanations

    references to orchestras and musical events

    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
    lier
    -0.08
    emas
    -0.08
    ioms
    -0.08
    slu
    -0.07
    Å¡tÄĽnÃŃ
    -0.07
    oog
    -0.07
    opl
    -0.07
    atty
    -0.06
    égorie
    -0.06
    ying
    -0.06
    POSITIVE LOGITS
    ItemClick
    0.07
    rary
    0.07
    ical
    0.06
    pedia
    0.06
    monic
    0.06
    arium
    0.06
    Quest
    0.06
     Friedman
    0.06
    atic
    0.06
     Ev
    0.06
    Activations Density 0.001%

    No Known Activations