© 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 EvalsExportsinterp-engineNEWAPI 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. 30432
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "This" and related phrases that indicate the beginning of a statement or explanation

    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
     Hin
    -0.07
    /*č↵
    -0.06
     Mang
    -0.06
    PARSE
    -0.06
    mine
    -0.06
    ë¨
    -0.06
    æĥij
    -0.06
     imp
    -0.06
     alm
    -0.06
    nest
    -0.06
    POSITIVE LOGITS
    оди
    0.06
    ateg
    0.06
    ilestone
    0.06
    atts
    0.06
    antes
    0.06
    Ģë¡ľ
    0.06
    uteur
    0.06
     funct
    0.06
    leitung
    0.06
     Voy
    0.06
    Activations Density 0.023%

    No Known Activations