© 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. 85111
    Prev
    Next
    INDEX
    Explanations

    mentions of diversity and variability in age, groups, platforms, messages, and experiences

    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
    uthor
    -0.07
    aktu
    -0.07
    .nih
    -0.07
    ất
    -0.07
    unca
    -0.07
    alle
    -0.07
    lew
    -0.07
     relegated
    -0.07
    illos
    -0.07
    adu
    -0.07
    POSITIVE LOGITS
     different
    0.15
     differently
    0.15
    different
    0.13
     Different
    0.12
    ä¸įåIJĮçļĦ
    0.12
    Different
    0.11
     diferentes
    0.11
    ä¸įåIJĮ
    0.11
     khác
    0.10
     diferente
    0.10
    Activations Density 0.027%

    No Known Activations