© 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. 89588
    Prev
    Next
    INDEX
    Explanations

    terms related to private initiatives and partnerships

    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
     and
    -0.08
    uras
    -0.07
     etc
    -0.07
     or
    -0.07
    以åıĬ
    -0.06
     various
    -0.06
     ones
    -0.06
    istrovstvÃŃ
    -0.06
     и
    -0.06
     &
    -0.06
    POSITIVE LOGITS
     piece
    0.09
    bie
    0.08
    ä¹ĭä¸Ģ
    0.07
    ìŀIJìĿ¸
    0.07
    presso
    0.07
    oru
    0.07
    ãģ£ãģ¡
    0.07
    جÙĩ
    0.07
    stroy
    0.07
    çļĦä¸Ģ个
    0.07
    Activations Density 0.061%

    No Known Activations