© 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. 27101
    Prev
    Next
    INDEX
    Explanations

    instances of inquiries and questions

    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
    UnderTest
    -0.07
    åĬ¨çĶŁæĪIJ
    -0.07
    CHASE
    -0.07
    ksen
    -0.07
    anst
    -0.07
    czy
    -0.07
    auge
    -0.07
    arl
    -0.07
    BITS
    -0.06
     mev
    -0.06
    POSITIVE LOGITS
     about
    0.09
    ainen
    0.07
     questions
    0.07
    about
    0.07
     Amber
    0.06
     amber
    0.06
     tentang
    0.06
    -about
    0.06
    çĸij
    0.06
     raised
    0.06
    Activations Density 0.009%

    No Known Activations