© 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. 9-LLAMASCOPE-RES-131K
    11. 99129
    Prev
    Next
    INDEX
    Explanations

    time and date references related to train schedules

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    feof
    -0.07
    GuidId
    -0.07
    fax
    -0.07
    CEEDED
    -0.07
    .transparent
    -0.07
    deniz
    -0.06
    تÙħر
    -0.06
    InParameter
    -0.06
    ÏĦÏĥ
    -0.06
    ILED
    -0.06
    POSITIVE LOGITS
    alla
    0.07
    iro
    0.07
    ideshow
    0.06
    883
    0.06
    .vn
    0.06
    баÑģ
    0.06
    udad
    0.05
    Ã
    0.05
     hob
    0.05
    pkg
    0.05
    Activations Density 0.001%

    No Known Activations