© 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. 69392
    Prev
    Next
    INDEX
    Explanations

    commands and configurations related to server settings

    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
    onder
    -0.07
    ByteArray
    -0.06
    anlar
    -0.06
    Å¡en
    -0.06
    rotch
    -0.06
    ÛĮدÛĮ
    -0.06
    iped
    -0.06
    insky
    -0.06
     reven
    -0.06
    ernet
    -0.06
    POSITIVE LOGITS
     вида
    0.07
     Controllers
    0.07
    [color
    0.06
    ENO
    0.06
    ego
    0.06
    uco
    0.06
    Charts
    0.06
     оÑĤноÑģ
    0.06
     Mich
    0.06
    uka
    0.06
    Activations Density 0.004%

    No Known Activations