© 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. 104131
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistics related to medical cases

    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
    inen
    -0.06
     Turtle
    -0.06
     turtle
    -0.06
    ught
    -0.06
     stew
    -0.05
    jan
    -0.05
     jerk
    -0.05
    bourg
    -0.05
     shaved
    -0.05
    uthor
    -0.05
    POSITIVE LOGITS
    GetProcAddress
    0.08
    ä¹ĭä¸Ģ
    0.07
    arih
    0.07
     Cout
    0.07
    (fabs
    0.06
    lake
    0.06
    ãĤ«ãĥ¼
    0.06
    uti
    0.06
    ceptar
    0.06
    _stylesheet
    0.06
    Activations Density 0.017%

    No Known Activations