© 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. 17-LLAMASCOPE-RES-131K
    11. 41229
    Prev
    Next
    INDEX
    Explanations

    references to editing and clarity in written communication

    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
    ór
    -0.06
    oken
    -0.06
    isz
    -0.06
     Carnegie
    -0.05
    urch
    -0.05
     statusCode
    -0.05
    atin
    -0.05
    ÙıÙĩ
    -0.05
    ål
    -0.05
    StatusLabel
    -0.05
    POSITIVE LOGITS
     Style
    0.07
    Style
    0.07
    ovice
    0.07
     style
    0.06
     ellipse
    0.06
     Fowler
    0.06
    DisplayStyle
    0.06
    loys
    0.06
    agraph
    0.06
    едагог
    0.06
    Activations Density 0.004%

    No Known Activations