© 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 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. 118715
    Prev
    Next
    INDEX
    Explanations

    mentions of female representation and contributions within the arts

    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
     cogn
    -0.06
     Com
    -0.06
    emem
    -0.06
    UiThread
    -0.06
     Rein
    -0.06
    io
    -0.05
     Aber
    -0.05
    eller
    -0.05
     Bat
    -0.05
     peg
    -0.05
    POSITIVE LOGITS
    future
    0.11
     future
    0.10
     continues
    0.09
    Future
    0.09
     Future
    0.09
     continue
    0.09
    _future
    0.08
    continue
    0.08
    æľªæĿ¥
    0.08
     futures
    0.08
    Activations Density 0.128%

    No Known Activations