© 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. 59429
    Prev
    Next
    INDEX
    Explanations

    references to the millennial generation and their 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
    och
    -0.07
    enguin
    -0.07
    ansom
    -0.07
    ymax
    -0.06
    lasses
    -0.06
     Kraj
    -0.06
    eson
    -0.06
    Çİ
    -0.06
    à¸Ľà¸£à¸°à¸ª
    -0.06
    ynet
    -0.06
    POSITIVE LOGITS
    ary
    0.09
    層
    0.09
    اÙĨÙĩ
    0.08
    -friendly
    0.07
    -era
    0.07
    aries
    0.07
    -aged
    0.07
    éłĥ
    0.07
     friendly
    0.06
    arie
    0.06
    Activations Density 0.004%

    No Known Activations