© 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. 73542
    Prev
    Next
    INDEX
    Explanations

    details related to lottery mechanics and winnings

    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
    odos
    -0.07
    ichi
    -0.07
    æ±ĩ
    -0.07
    UILTIN
    -0.07
    quet
    -0.07
     zug
    -0.07
     Sanayi
    -0.06
    елÑİ
    -0.06
    .CV
    -0.06
    kie
    -0.06
    POSITIVE LOGITS
    gnore
    0.06
     Maz
    0.06
    ÃŃst
    0.06
    ãĥ³ãĥĸ
    0.06
     selv
    0.06
    /UIKit
    0.06
    yun
    0.06
    lesh
    0.05
    reh
    0.05
     Prest
    0.05
    Activations Density 0.003%

    No Known Activations