© 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. 121628
    Prev
    Next
    INDEX
    Explanations

    method calls and their parameters in programming code

    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
    esome
    -0.08
    umba
    -0.07
    exus
    -0.07
    lesia
    -0.07
    indir
    -0.07
    agar
    -0.07
    IELDS
    -0.06
    à¸ģรรม
    -0.06
    elas
    -0.06
    ongsTo
    -0.06
    POSITIVE LOGITS
    rell
    0.07
    int
    0.06
    ffen
    0.06
    illon
    0.06
    chu
    0.06
    hek
    0.06
    itters
    0.06
    dol
    0.06
    дÑĢом
    0.06
    åľŃ
    0.06
    Activations Density 0.000%

    No Known Activations