© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95180
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to navigation menus in web development

    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
    Calibri
    -0.08
    inch
    -0.08
     undermin
    -0.07
    ÚĨÙĩ
    -0.07
     ogl
    -0.07
    ]--;↵
    -0.07
    Scrollbar
    -0.07
    arya
    -0.07
    izedName
    -0.07
     INTERRUPTION
    -0.06
    POSITIVE LOGITS
    func
    0.06
    iropr
    0.06
    olson
    0.06
    atu
    0.06
     yön
    0.06
    .getError
    0.06
    زار
    0.05
     Tol
    0.05
    structor
    0.05
     Schedule
    0.05
    Activations Density 0.011%

    No Known Activations