© 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 EvalsExportsinterp-engineNEWAPI 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. 105208
    Prev
    Next
    INDEX
    Explanations

    common game mechanics and actions

    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
    bic
    -0.07
    olet
    -0.07
    egin
    -0.07
    ubic
    -0.07
    ">//
    -0.07
    _stride
    -0.06
    oload
    -0.06
    mlink
    -0.06
    .stride
    -0.06
    iad
    -0.06
    POSITIVE LOGITS
     titular
    0.07
    ARIO
    0.07
    .resume
    0.06
     goal
    0.06
     unst
    0.06
     viên
    0.06
    jes
    0.06
     try
    0.06
     obstacles
    0.06
    (blocks
    0.06
    Activations Density 0.037%

    No Known Activations