© 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. 9-LLAMASCOPE-RES-131K
    11. 93984
    Prev
    Next
    INDEX
    Explanations

    instances of personal reflections and evaluations in texts

    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
    poser
    -0.07
    istrov
    -0.07
    perf
    -0.07
    izmet
    -0.07
    ãĤĮãģ©
    -0.07
    elmet
    -0.07
    bris
    -0.06
    Å¡il
    -0.06
    ondo
    -0.06
    robat
    -0.06
    POSITIVE LOGITS
    UIL
    0.06
     Doming
    0.06
     bon
    0.06
     chair
    0.06
    ular
    0.06
    ks
    0.06
     z
    0.06
    ÃŃ
    0.06
     aur
    0.06
     å¹
    0.06
    Activations Density 0.001%

    No Known Activations