© 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. 39025
    Prev
    Next
    INDEX
    Explanations

    patterns related to code structure and formatting

    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
    acock
    -0.07
    tn
    -0.06
    xy
    -0.06
    жÑĥ
    -0.06
    mland
    -0.06
    irim
    -0.06
    дÑĥ
    -0.06
    аÑİ
    -0.06
    ague
    -0.06
    ersh
    -0.06
    POSITIVE LOGITS
    ersist
    0.07
    RTL
    0.06
    .scenes
    0.06
    iên
    0.06
     porr
    0.06
    ucle
    0.06
    modulo
    0.06
    |required
    0.06
    htm
    0.06
    keywords
    0.06
    Activations Density 0.000%

    No Known Activations