© 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. 94596
    Prev
    Next
    INDEX
    Explanations

    monetary figures related to funding and financial transactions

    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
    æµľ
    -0.07
    /epl
    -0.07
    á»ĭ
    -0.07
    zell
    -0.07
    VRT
    -0.07
    SceneManager
    -0.07
     Madden
    -0.07
    cmc
    -0.07
     Kami
    -0.06
    addock
    -0.06
    POSITIVE LOGITS
    uit
    0.06
     according
    0.06
    edback
    0.06
    Essay
    0.06
     gal
    0.06
     in
    0.06
    pec
    0.06
    Brief
    0.06
    ĺ认
    0.06
    .runner
    0.06
    Activations Density 0.011%

    No Known Activations