© 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. 69284
    Prev
    Next
    INDEX
    Explanations

    elements and conditions related to SQL queries and data handling

    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
    hone
    -0.06
    iske
    -0.06
    ìĸ´
    -0.06
    rob
    -0.06
    linkplain
    -0.06
    tel
    -0.06
    æľº
    -0.06
    breaking
    -0.06
    bubble
    -0.06
    toi
    -0.06
    POSITIVE LOGITS
    owitz
    0.08
    ityEngine
    0.07
    ather
    0.07
    ande
    0.06
    VisualStyle
    0.06
    AndView
    0.06
    ometown
    0.06
    ERE
    0.06
    ãĤ¹ãĥĨ
    0.06
    OrderBy
    0.06
    Activations Density 0.009%

    No Known Activations