© 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. 89842
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and their usage in expressions of personal experiences or opinions

    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
    MimeType
    -0.09
    بÙĪاسطة
    -0.09
    >NN
    -0.08
    chyb
    -0.08
    ignum
    -0.08
    _tF
    -0.08
    yonel
    -0.08
    usercontent
    -0.08
    oldown
    -0.08
    øre
    -0.08
    POSITIVE LOGITS
     lou
    0.07
     mean
    0.06
    -
    0.06
    AY
    0.06
    e
    0.06
    olo
    0.06
    .
    0.06
    335
    0.06
     &
    0.06
    Âł
    0.06
    Activations Density 0.011%

    No Known Activations