© 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. 116577
    Prev
    Next
    INDEX
    Explanations

    negative values or indicators in quantitative data analyses

    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
    sp
    -0.06
    blings
    -0.06
    ..↵
    -0.06
    âĢ¦↵
    -0.06
     unf
    -0.06
    2
    -0.06
     frog
    -0.06
    stick
    -0.06
    eld
    -0.06
    å¾Ħ
    -0.06
    POSITIVE LOGITS
    .binding
    0.09
    uzz
    0.08
    ott
    0.08
    ãĤ¤ãĤº
    0.08
    Gratis
    0.08
    -widgets
    0.08
     èĭ¥è¦ģ
    0.08
    Türkiye
    0.08
     ÄIJá»ĭnh
    0.07
    gratis
    0.07
    Activations Density 0.019%

    No Known Activations