© 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. 96219
    Prev
    Next
    INDEX
    Explanations

    terms related to customer service and product offerings

    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
    432
    -0.06
    usable
    -0.06
    hi
    -0.06
    åħ¸
    -0.05
     convention
    -0.05
    cket
    -0.05
    ip
    -0.05
    باد
    -0.05
     Edgar
    -0.05
     Datensch
    -0.05
    POSITIVE LOGITS
     vuông
    0.08
    .qual
    0.07
    rypton
    0.07
    Dispatch
    0.07
    chwitz
    0.07
    ifikasi
    0.07
    slaught
    0.07
    .gb
    0.06
    _SCRIPT
    0.06
     íĨµ
    0.06
    Activations Density 0.001%

    No Known Activations