© 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. 5996
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically their frequency and context within 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
    ib
    -0.06
    Fixture
    -0.06
    skins
    -0.06
    IRMWARE
    -0.06
     Ñĥг
    -0.06
    aises
    -0.06
    iske
    -0.06
    lands
    -0.06
     åį
    -0.05
    947
    -0.05
    POSITIVE LOGITS
    antu
    0.07
    AO
    0.07
     Afterwards
    0.07
    achat
    0.07
     afterward
    0.07
    inda
    0.07
    gu
    0.06
    abinet
    0.06
    LET
    0.06
    ido
    0.06
    Activations Density 0.023%

    No Known Activations