© 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. 79033
    Prev
    Next
    INDEX
    Explanations

    second-person pronouns and related phrases indicating advice or personal instructions

    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
    xima
    -0.07
    nte
    -0.07
    qli
    -0.07
    Å¡k
    -0.06
    ÑĤÑĢ
    -0.06
    posables
    -0.06
    las
    -0.06
    agas
    -0.06
    .Modules
    -0.06
    ernes
    -0.06
    POSITIVE LOGITS
     èĴ
    0.07
    oze
    0.06
    linger
    0.06
    /Create
    0.06
     deleg
    0.06
     âĸĪ
    0.06
    .LayoutStyle
    0.06
    ictim
    0.05
     bu
    0.05
    ader
    0.05
    Activations Density 0.015%

    No Known Activations