© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    references to music albums or songs

    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
    URT
    -0.06
    ooks
    -0.06
    oj
    -0.06
    .lp
    -0.06
    >Main
    -0.06
    ãģĵãģĨ
    -0.06
    ailer
    -0.06
    rana
    -0.05
    uchen
    -0.05
    etur
    -0.05
    POSITIVE LOGITS
    ONTAL
    0.08
    ëħĦëıĦ
    0.07
    .ArgumentParser
    0.07
    akis
    0.07
    ë¡Ģ
    0.07
    "path
    0.06
    .volley
    0.06
    ÑĢеÑģ
    0.06
    رÙĬس
    0.06
    agrant
    0.06
    Activations Density 0.015%

    No Known Activations