© 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. 118833
    Prev
    Next
    INDEX
    Explanations

    HTML and script tag elements in the document

    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
    ĤŃ
    -0.07
     introdu
    -0.07
    rtype
    -0.06
    ãĥ¼ãĤº
    -0.06
     UPLOAD
    -0.06
    htdocs
    -0.06
    pus
    -0.06
    _FULLSCREEN
    -0.06
     æĹ
    -0.06
    ÑĨей
    -0.06
    POSITIVE LOGITS
     copyright
    0.14
    opyright
    0.13
    copyright
    0.13
    footer
    0.13
    Copyright
    0.13
    /footer
    0.13
     Footer
    0.13
     footer
    0.12
     Copyright
    0.12
     copyrights
    0.12
    Activations Density 0.018%

    No Known Activations