© 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. 9-LLAMASCOPE-RES-131K
    11. 99000
    Prev
    Next
    INDEX
    Explanations

    occurrences of special characters or symbols in the text

    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
    pcl
    -0.07
    rex
    -0.07
    оÑĢд
    -0.07
    алеж
    -0.07
    ligt
    -0.06
     opposite
    -0.06
    theros
    -0.06
    icious
    -0.06
    .Unity
    -0.06
     erfolgre
    -0.06
    POSITIVE LOGITS
    itori
    0.06
     Lamb
    0.06
    »
    0.06
    ainty
    0.06
    ETY
    0.06
    ëĦ·
    0.06
    ügen
    0.06
     dearly
    0.06
    å¼¥
    0.06
    ocks
    0.06
    Activations Density 0.002%

    No Known Activations