© 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. 125733
    Prev
    Next
    INDEX
    Explanations

    references to significant events or concepts related to time

    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
     one
    -0.08
    meric
    -0.06
    ioso
    -0.06
    aled
    -0.06
    ÄĽk
    -0.06
    eyse
    -0.06
    awah
    -0.06
    ÑĪÑĤов
    -0.06
    _inches
    -0.06
    witter
    -0.05
    POSITIVE LOGITS
    ãĢģäºĮ
    0.09
     wonders
    0.09
    ìĶ©
    0.08
    éĥİ
    0.08
    portun
    0.08
    atat
    0.07
     liners
    0.07
    -third
    0.07
    edly
    0.07
    -click
    0.06
    Activations Density 0.058%

    No Known Activations