© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95393
    Prev
    Next
    INDEX
    Explanations

    occurrences of method definitions and declarations in code

    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
    oram
    -0.08
    uibModal
    -0.07
    atorium
    -0.07
    CallCheck
    -0.07
    MLS
    -0.07
    aldo
    -0.07
    _refl
    -0.07
    dex
    -0.07
    /WebAPI
    -0.07
    rowse
    -0.07
    POSITIVE LOGITS
     split
    0.07
    ician
    0.06
     circ
    0.06
    omor
    0.06
    zhou
    0.06
     سÙģ
    0.06
    iyah
    0.06
    urtle
    0.06
    _sta
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Activations Density 0.013%

    No Known Activations