© 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. 18553
    Prev
    Next
    INDEX
    Explanations

    references to statistics and data regarding infant mortality

    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
     вÑĭÑħод
    -0.06
    樹
    -0.06
     innoc
    -0.06
     asset
    -0.06
    ãĤ¥
    -0.06
     defer
    -0.06
    gaard
    -0.06
     host
    -0.06
     बद
    -0.06
    aticon
    -0.06
    POSITIVE LOGITS
     records
    0.09
    records
    0.08
     Record
    0.08
     record
    0.08
     Records
    0.08
    æŃ»
    0.08
     death
    0.08
     reporting
    0.08
     Reporting
    0.08
     data
    0.07
    Activations Density 0.015%

    No Known Activations