© 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. 120380
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to programming concepts and data 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
     Ans
    -0.07
    uard
    -0.06
    uide
    -0.06
    itä
    -0.06
    stro
    -0.06
    ugin
    -0.06
    ait
    -0.06
    uit
    -0.06
    /commons
    -0.06
     kadar
    -0.05
    POSITIVE LOGITS
     Surre
    0.07
     заÑĢаз
    0.07
    ufe
    0.07
     dÄ±ÅŁÄ±
    0.07
     Ruth
    0.06
    regor
    0.06
    à¸Īร
    0.06
    леÑĩ
    0.06
    .pm
    0.06
    aliyet
    0.06
    Activations Density 0.007%

    No Known Activations