© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83467
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code structure

    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
    ihu
    -0.07
     Wenger
    -0.07
    exas
    -0.07
    BindingUtil
    -0.07
    iku
    -0.07
    gii
    -0.06
    ocz
    -0.06
    innacle
    -0.06
    láš
    -0.06
     rolling
    -0.06
    POSITIVE LOGITS
    opes
    0.07
     XMLHttpRequest
    0.07
     zor
    0.06
    lob
    0.06
    /gallery
    0.06
     atom
    0.06
     mime
    0.06
    имв
    0.06
    ÏĦον
    0.06
    оÑĢд
    0.06
    Activations Density 0.012%

    No Known Activations