© 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. 63253
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prior" indicating preconditions or prerequisites

    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
    end
    -0.07
    æĽľæĹ¥
    -0.06
    vin
    -0.06
    -bordered
    -0.06
    rey
    -0.06
    enden
    -0.06
    ارÙĩ
    -0.06
    ible
    -0.06
    ÙģØ´
    -0.06
    cock
    -0.06
    POSITIVE LOGITS
    /post
    0.10
    (before
    0.08
    /current
    0.08
    itize
    0.07
    lease
    0.07
    ities
    0.07
    itaire
    0.07
    mente
    0.07
    uly
    0.07
    ordial
    0.07
    Activations Density 0.010%

    No Known Activations