© 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. 5748
    Prev
    Next
    INDEX
    Explanations

    information related to loan repayment and forgiveness programs for healthcare and legal professionals

    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
    linger
    -0.07
     isNaN
    -0.07
    ácil
    -0.06
    edList
    -0.06
     Bever
    -0.06
    labs
    -0.06
     further
    -0.06
     Germ
    -0.06
    acerb
    -0.06
    KeyName
    -0.06
    POSITIVE LOGITS
    Įĵ
    0.08
    емон
    0.07
    828
    0.07
    563
    0.07
     individuals
    0.07
    oving
    0.06
     pairs
    0.06
    emon
    0.06
     Subset
    0.06
    ost
    0.06
    Activations Density 0.048%

    No Known Activations