© 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. 63086
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific variables related to mathematical and computational contexts

    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
    воÑİ
    -0.07
    ÅĻeh
    -0.06
     sonu
    -0.06
     yiy
    -0.06
    iff
    -0.06
    å·¦åı³
    -0.06
    ãģİ
    -0.06
    StreamWriter
    -0.06
     care
    -0.06
    ssc
    -0.06
    POSITIVE LOGITS
    utow
    0.07
    632
    0.07
    000
    0.06
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.06
    415
    0.06
    ADDE
    0.06
    ament
    0.06
    λÏī
    0.06
    553
    0.06
     Rudy
    0.06
    Activations Density 0.042%

    No Known Activations