© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91691
    Prev
    Next
    INDEX
    Explanations

    corporate names and their stock ticker symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    mente
    -0.07
     bol
    -0.07
    ÑĪибка
    -0.06
     gre
    -0.06
    è¶
    -0.06
     Roths
    -0.06
     liter
    -0.06
    دا
    -0.06
     ren
    -0.05
    tf
    -0.05
    POSITIVE LOGITS
    okino
    0.07
     Abstract
    0.07
    ãĥ³ãĥIJ
    0.07
    ruba
    0.06
    >NN
    0.06
    ourn
    0.06
    icode
    0.06
    unma
    0.06
    @Web
    0.06
    ëį°ìĿ´íĬ¸
    0.06
    Activations Density 0.000%

    No Known Activations