© 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. 15575
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or contexts in mathematical or scholarly discussions

    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
    ugg
    -0.07
    ÑĢеменно
    -0.06
    isia
    -0.06
    kö
    -0.06
    orraine
    -0.06
    acio
    -0.06
     olm
    -0.06
    ä¸Ī
    -0.06
    emics
    -0.06
     vigor
    -0.06
    POSITIVE LOGITS
    unately
    0.08
     convenience
    0.07
    ymm
    0.07
    âce
    0.07
    378
    0.07
     example
    0.07
     ActionTypes
    0.07
    bish
    0.07
     purposes
    0.06
    given
    0.06
    Activations Density 0.032%

    No Known Activations