© 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. 123356
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks typically associated with programming or code syntax

    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
    eview
    -0.06
    leaf
    -0.06
     Roberts
    -0.06
     openFileDialog
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    ç
    -0.06
    :param
    -0.05
    -desktop
    -0.05
    elf
    -0.05
    ález
    -0.05
    POSITIVE LOGITS
    odie
    0.06
     /*!<
    0.06
    exampleInput
    0.06
    byname
    0.06
    teri
    0.06
    ISBN
    0.06
     soo
    0.06
    redi
    0.06
    casts
    0.06
    .TryParse
    0.06
    Activations Density 0.030%

    No Known Activations