© 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. 38517
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and economic issues impacting vulnerable populations

    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
     instead
    -0.08
     almost
    -0.07
     exactly
    -0.07
     again
    -0.07
     both
    -0.07
    instead
    -0.06
    :
    -0.06
     formal
    -0.06
    .ul
    -0.06
    almost
    -0.06
    POSITIVE LOGITS
     بÙĦÚ©Ùĩ
    0.09
     nor
    0.09
     sondern
    0.08
     ê·¸ëłĩ
    0.08
    -exclusive
    0.08
     necessarily
    0.08
     anymore
    0.07
    nor
    0.07
    tings
    0.07
    ProgressHUD
    0.07
    Activations Density 0.011%

    No Known Activations