© 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. 79995
    Prev
    Next
    INDEX
    Explanations

    references to energy storage technologies and their applications

    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
     substance
    -0.07
    imei
    -0.07
    ande
    -0.07
    Verdana
    -0.07
    igos
    -0.07
    ahy
    -0.07
    arma
    -0.07
    celik
    -0.06
    ladu
    -0.06
    getOption
    -0.06
    POSITIVE LOGITS
    .opensource
    0.07
     vehicles
    0.06
    ord
    0.06
     demanding
    0.06
    bounds
    0.06
     powering
    0.06
     box
    0.06
    olest
    0.06
     Doll
    0.06
     mini
    0.06
    Activations Density 0.045%

    No Known Activations