© 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. 94398
    Prev
    Next
    INDEX
    Explanations

    code-related documentation comments and formatting tags

    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
    ngrx
    -0.08
    asio
    -0.07
    सà¤Ń
    -0.07
    kses
    -0.07
    ubby
    -0.07
    .Hosting
    -0.07
    echa
    -0.07
    istrovstvÃŃ
    -0.07
    rouw
    -0.07
    loi
    -0.06
    POSITIVE LOGITS
     public
    0.07
     constructor
    0.07
    318
    0.06
     Constructor
    0.06
    ery
    0.06
     sod
    0.06
     ctor
    0.06
     InitializeComponent
    0.06
    constructor
    0.06
    _expand
    0.06
    Activations Density 0.003%

    No Known Activations