© 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. 92449
    Prev
    Next
    INDEX
    Explanations

    programming syntax and annotations

    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
    inely
    -0.07
    quo
    -0.07
    rnek
    -0.07
    mage
    -0.07
    oulder
    -0.07
    enna
    -0.07
    dni
    -0.07
    ingo
    -0.07
    kul
    -0.07
    -CN
    -0.07
    POSITIVE LOGITS
     *((
    0.06
    dd
    0.06
    eniz
    0.06
    omin
    0.06
    (æ°´
    0.06
     Ade
    0.06
    ÏĥÏĦή
    0.06
     zá
    0.06
    ÑĪка
    0.05
    542
    0.05
    Activations Density 0.000%

    No Known Activations