© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 128891
    Prev
    Next
    INDEX
    Explanations

    references to bags and carrying-related items

    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
    lando
    -0.07
     aba
    -0.07
    ëij¥
    -0.07
    elpers
    -0.07
    597
    -0.07
    _plate
    -0.07
     Tank
    -0.07
    Tank
    -0.06
    rig
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
     containing
    0.09
    gy
    0.07
    gie
    0.07
    gage
    0.07
    -shaped
    0.07
    gages
    0.07
    Contents
    0.07
    alom
    0.07
     contents
    0.07
    ruptcy
    0.07
    Activations Density 0.015%

    No Known Activations