© 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. 42274
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation, particularly concerning human actions and their implications

    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
    ãĥ»ãĥ»ãĥ»↵↵
    -0.07
    ĥ½
    -0.07
    анÑģов
    -0.07
    ÅĻÃŃz
    -0.07
    HANDLE
    -0.07
    lid
    -0.07
    chwitz
    -0.07
    LEAR
    -0.07
     halinde
    -0.07
    loff
    -0.07
    POSITIVE LOGITS
     factors
    0.07
     rather
    0.07
     something
    0.07
     processes
    0.07
     Factors
    0.07
    ijo
    0.06
     Something
    0.06
     sources
    0.06
    omething
    0.06
    ips
    0.06
    Activations Density 0.037%

    No Known Activations