© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87558
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotional connections to music and films

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ovsky
    -0.07
    _heads
    -0.07
    ogn
    -0.06
    ='../
    -0.06
    antanamo
    -0.06
     Millet
    -0.06
    auty
    -0.06
     Trend
    -0.06
    roups
    -0.06
    ToPoint
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
     songs
    0.07
    _CANNOT
    0.07
    ÃŃd
    0.07
    ály
    0.06
    EFR
    0.06
    aldo
    0.06
    Ø®ÙĪ
    0.06
    FXML
    0.06
    urga
    0.06
    Activations Density 0.013%

    No Known Activations