© 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. 99220
    Prev
    Next
    INDEX
    Explanations

    specific brand names, especially in the automotive industry

    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
     Hin
    -0.06
    isi
    -0.06
    ens
    -0.06
    mouth
    -0.06
    enden
    -0.06
     Heading
    -0.06
    ulk
    -0.06
    ensive
    -0.06
     et
    -0.06
     Zw
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    ovÃŃ
    0.07
    омеÑĢ
    0.07
    ëł´
    0.07
    Copying
    0.07
     Ñħими
    0.07
    ìŀ¥ìĿĦ
    0.07
    ÙģاÙĤ
    0.07
    ÙĨدر
    0.07
    ãĤ¿ãĥ«
    0.06
    Activations Density 0.078%

    No Known Activations