© 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. 80728
    Prev
    Next
    INDEX
    Explanations

    elements related to table formatting and structure in documents

    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
    iesta
    -0.07
    iasi
    -0.07
    aida
    -0.07
    æĽ²
    -0.07
    ιÏĩ
    -0.07
     fitte
    -0.07
    اÛĮÙĩ
    -0.07
    artment
    -0.07
    .libs
    -0.07
    ombat
    -0.06
    POSITIVE LOGITS
     colspan
    0.07
    ocker
    0.06
     rowspan
    0.06
     Kle
    0.06
    eniz
    0.06
    UDIO
    0.06
    ULL
    0.06
    yer
    0.06
    çĤ¹
    0.06
    ³
    0.06
    Activations Density 0.002%

    No Known Activations