© 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. 41432
    Prev
    Next
    INDEX
    Explanations

    references to birth years and categories related to people and entities

    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
    dio
    -0.07
    ending
    -0.06
    apor
    -0.06
    bor
    -0.06
    meg
    -0.06
    ENDING
    -0.06
    ÑĪив
    -0.06
    elik
    -0.06
    èĤ
    -0.06
     Meg
    -0.06
    POSITIVE LOGITS
    urovision
    0.07
    izens
    0.07
    aternity
    0.06
     defe
    0.06
    à¤ľà¤¨
    0.06
    antar
    0.06
    ucu
    0.06
    ounced
    0.06
    :UIAlert
    0.06
    oku
    0.06
    Activations Density 0.001%

    No Known Activations