© 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. 61371
    Prev
    Next
    INDEX
    Explanations

    gerunds and other verb forms associated with ongoing actions and activities

    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
    vik
    -0.07
    agen
    -0.07
    arge
    -0.07
    imu
    -0.07
    ande
    -0.07
    hek
    -0.07
    /current
    -0.07
    gni
    -0.06
     Meadows
    -0.06
    yet
    -0.06
    POSITIVE LOGITS
    udeau
    0.07
    ibold
    0.07
    -related
    0.07
    lrt
    0.07
    NotSupportedException
    0.06
     guru
    0.06
    uali
    0.06
    imore
    0.06
    ioni
    0.06
    923
    0.06
    Activations Density 0.094%

    No Known Activations