© 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. 59876
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" indicating personal experiences or actions

    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
    -alist
    -0.07
    alink
    -0.06
    undy
    -0.06
    å·»
    -0.06
    patch
    -0.06
    adr
    -0.06
    _magic
    -0.06
    оген
    -0.06
    pac
    -0.06
    ĥ
    -0.06
    POSITIVE LOGITS
     try
    0.08
     attempt
    0.07
    try
    0.07
     run
    0.06
     trying
    0.06
     tries
    0.06
    SharedPtr
    0.06
     kabil
    0.06
    trying
    0.06
    richt
    0.06
    Activations Density 0.010%

    No Known Activations