© 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. 15-LLAMASCOPE-RES-131K
    11. 87375
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and constructs

    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
    eden
    -0.07
    aked
    -0.06
    .vert
    -0.06
     nto
    -0.06
     >",
    -0.06
     Mil
    -0.06
    esch
    -0.06
    _retry
    -0.06
    owied
    -0.06
    esa
    -0.06
    POSITIVE LOGITS
    isto
    0.07
    sembl
    0.07
    ÑĦеÑĢ
    0.07
    oco
    0.07
     Pou
    0.06
    aps
    0.06
    à¥įरम
    0.06
     straw
    0.06
    ICLES
    0.06
    име
    0.06
    Activations Density 0.001%

    No Known Activations