© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14450
    Prev
    Next
    INDEX
    Explanations

    text related to time and dates

    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
    دار
    -0.08
     æĹ¥æľŁ
    -0.07
    顶
    -0.07
     November
    -0.07
    (CultureInfo
    -0.07
    dds
    -0.07
     March
    -0.07
    asset
    -0.07
    ©©
    -0.07
    éŨ
    -0.07
    POSITIVE LOGITS
     issue
    0.07
    orig
    0.07
     https
    0.06
     pp
    0.06
    ored
    0.06
    nde
    0.06
    https
    0.06
    issue
    0.06
    ære
    0.05
    ayne
    0.05
    Activations Density 0.023%

    No Known Activations