© 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. 63116
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and anticipation

    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
    erk
    -0.07
    hee
    -0.07
    clearfix
    -0.06
    cek
    -0.06
    à¹Ħหà¸Ļ
    -0.06
    alous
    -0.06
    段
    -0.06
    ummy
    -0.06
    remen
    -0.06
     Incontri
    -0.06
    POSITIVE LOGITS
    ahir
    0.08
     hoping
    0.07
     hopes
    0.07
    .syntax
    0.07
     hoped
    0.07
     hope
    0.07
     Nug
    0.07
     rằng
    0.06
     Bale
    0.06
    StackSize
    0.06
    Activations Density 0.006%

    No Known Activations