© 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. 89175
    Prev
    Next
    INDEX
    Explanations

    C++ programming syntax and 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
    olver
    -0.06
    az
    -0.06
    able
    -0.06
    ambiguous
    -0.06
    woord
    -0.06
     Kinder
    -0.06
    ftware
    -0.06
    ingroup
    -0.06
    udur
    -0.06
    ä¸Ģç§į
    -0.05
    POSITIVE LOGITS
    gren
    0.08
    sy
    0.08
    ÑĩаÑģ
    0.08
    sWith
    0.07
    mers
    0.07
    tember
    0.07
    lesi
    0.07
    s
    0.07
    enton
    0.07
    ERGE
    0.07
    Activations Density 0.004%

    No Known Activations