© 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. 123280
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities associated with ingredients in recipes

    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
    ernel
    -0.07
    еÑģÑĤи
    -0.07
    lah
    -0.07
    IMER
    -0.07
    ils
    -0.07
    еÑģÑĤÑĮ
    -0.07
     UIBar
    -0.07
    ané
    -0.06
    emin
    -0.06
    tar
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.06
    OfDay
    0.06
    <=(
    0.06
     heir
    0.06
     dozen
    0.06
    .scalablytyped
    0.06
    OfYear
    0.06
    ths
    0.06
    prene
    0.06
     del
    0.06
    Activations Density 0.015%

    No Known Activations