© 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. 55020
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    INARY
    -0.07
    ecko
    -0.07
    idot
    -0.07
     Sab
    -0.07
    Spo
    -0.07
    ocking
    -0.07
    áºł
    -0.07
    ugu
    -0.07
    bedo
    -0.06
    ç«ĭãģ¡
    -0.06
    POSITIVE LOGITS
     Counter
    0.06
     Gon
    0.06
     xứ
    0.06
     wor
    0.06
     counter
    0.06
     AVC
    0.06
     reading
    0.06
    ardo
    0.06
    .hadoop
    0.06
    equip
    0.05
    Activations Density 0.009%

    No Known Activations