© 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. 89644
    Prev
    Next
    INDEX
    Explanations

    specific special characters and formatting 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
    GPL
    -0.07
    ucas
    -0.07
    ivot
    -0.07
    opensource
    -0.06
    erd
    -0.06
     ><?
    -0.06
    itet
    -0.06
    vla
    -0.06
    bard
    -0.06
    ahn
    -0.06
    POSITIVE LOGITS
    ná
    0.06
     UNUSED
    0.06
    uelle
    0.06
    abus
    0.06
    olle
    0.06
    lon
    0.05
    PT
    0.05
    idor
    0.05
    lyn
    0.05
    ió
    0.05
    Activations Density 0.000%

    No Known Activations