© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55562
    Prev
    Next
    INDEX
    Explanations

    references to characters and their actions within narratives

    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
    datatable
    -0.07
    ãĥ¼ãĥª
    -0.07
    aint
    -0.06
    eri
    -0.06
    THR
    -0.06
    ↵↵
    -0.06
    lopen
    -0.06
     Haram
    -0.06
    469
    -0.06
    ï¿
    -0.06
    POSITIVE LOGITS
    chez
    0.07
    »
    0.07
     aforementioned
    0.06
     multin
    0.06
     Îŀ
    0.06
    unch
    0.06
     ****************************************************************************
    0.06
    viz
    0.06
    azzo
    0.06
    ocoder
    0.06
    Activations Density 0.000%

    No Known Activations