© 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. 96179
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or code structures

    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
    lingen
    -0.06
     Gors
    -0.06
    avis
    -0.06
    /render
    -0.06
    imity
    -0.06
     Hart
    -0.06
    chet
    -0.06
    lobe
    -0.06
    лоÑĩ
    -0.06
    .synthetic
    -0.05
    POSITIVE LOGITS
    azo
    0.07
    füg
    0.07
    apolis
    0.07
    جÙĬ
    0.06
    adle
    0.06
    wick
    0.06
    ENDOR
    0.06
    azi
    0.06
    ãĥ«ãĥī
    0.06
    ostat
    0.06
    Activations Density 0.008%

    No Known Activations