© 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. 91746
    Prev
    Next
    INDEX
    Explanations

    references to people named Nadine or related forms of the name

    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
    erie
    -0.08
    sis
    -0.07
    iya
    -0.07
    IEW
    -0.07
    quila
    -0.07
    sf
    -0.07
    aan
    -0.07
    _suite
    -0.07
    orio
    -0.07
    NAMESPACE
    -0.07
    POSITIVE LOGITS
    ĽĪ
    0.07
    ipur
    0.07
    asso
    0.07
    ask
    0.07
    ular
    0.06
    avit
    0.06
    imuth
    0.06
    erno
    0.06
    uno
    0.06
    212
    0.06
    Activations Density 0.003%

    No Known Activations