© 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. 105017
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and experiences

    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
    roje
    -0.07
    ijd
    -0.07
    باÙĨ
    -0.07
    ffic
    -0.06
    elcome
    -0.06
     dames
    -0.06
    uze
    -0.06
    ì¢Į
    -0.06
    iley
    -0.06
    atcher
    -0.06
    POSITIVE LOGITS
     extremes
    0.06
     site
    0.06
    edges
    0.06
    773
    0.06
     polls
    0.06
     unfamiliar
    0.06
     edge
    0.06
     showers
    0.06
     heart
    0.06
    istrovstvÃŃ
    0.06
    Activations Density 0.027%

    No Known Activations