© 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. 15257
    Prev
    Next
    INDEX
    Explanations

    elements of programming code involving object-oriented design and error handling

    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
    isko
    -0.07
    ëŁ¼
    -0.07
    ovan
    -0.06
    <TResult
    -0.06
     mornings
    -0.06
    izzo
    -0.06
    .xlsx
    -0.06
    jak
    -0.06
     Esk
    -0.06
    imu
    -0.06
    POSITIVE LOGITS
    atk
    0.07
    ิà¸Ļà¸Ķ
    0.06
    .BLL
    0.06
     partial
    0.06
    IDX
    0.06
    yne
    0.06
    .slim
    0.06
    ÑĥÑĤи
    0.06
     squat
    0.06
    aylor
    0.06
    Activations Density 0.081%

    No Known Activations