© 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. 15-LLAMASCOPE-RES-131K
    11. 87124
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to astronomical measurements and observations

    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
    rox
    -0.07
    utzer
    -0.06
     Barb
    -0.06
     undisclosed
    -0.06
    lights
    -0.06
    ãİ¡
    -0.06
    ayet
    -0.06
     smarty
    -0.06
    -cycle
    -0.06
     Leban
    -0.06
    POSITIVE LOGITS
     Radio
    0.09
     radio
    0.09
    Radio
    0.08
    á»ĩn
    0.08
     headphones
    0.07
    radio
    0.07
     Amateur
    0.07
     listening
    0.07
    bsub
    0.07
     listened
    0.07
    Activations Density 0.109%

    No Known Activations