© 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 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. 40405
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs related to programming or software functionality

    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
     playa
    -0.06
     gridColumn
    -0.06
     Hollow
    -0.06
    ounding
    -0.06
    ÑģÑĤа
    -0.06
    assen
    -0.06
    WEBPACK
    -0.06
     xlink
    -0.06
     vmax
    -0.06
    missive
    -0.05
    POSITIVE LOGITS
    .Bot
    0.08
    _markup
    0.07
    .Automation
    0.07
     Keyboard
    0.07
     Miami
    0.07
    ikki
    0.07
     NDEBUG
    0.07
    ëĭ¨ì²´
    0.06
    mens
    0.06
    edException
    0.06
    Activations Density 0.005%

    No Known Activations