© 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. 42783
    Prev
    Next
    INDEX
    Explanations

    mentions of days and events that involve activities or trips

    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
    xit
    -0.07
     nights
    -0.07
    weed
    -0.07
     Nights
    -0.07
    elu
    -0.06
    ÑĨÑİ
    -0.06
    chas
    -0.06
     nightly
    -0.06
     evenings
    -0.06
    otti
    -0.06
    POSITIVE LOGITS
     spent
    0.10
    -long
    0.08
    ÐŁÐļ
    0.08
    eday
    0.08
    long
    0.07
    spent
    0.07
     devoted
    0.07
     @"↵
    0.07
     spend
    0.06
     Ler
    0.06
    Activations Density 0.015%

    No Known Activations