© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59133
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ["$
    -0.09
    .strict
    -0.09
     ëĦ¤ìĿ´íĬ¸
    -0.09
    .Currency
    -0.08
    .Selenium
    -0.08
    ë¡ľëĤĺ
    -0.08
    .CG
    -0.08
    !↵↵↵↵
    -0.08
    .getElements
    -0.08
    NullException
    -0.08
    POSITIVE LOGITS
    ↵
    0.06
    ..↵
    0.06
    ead
    0.06
    ente
    0.05
     outnumber
    0.05
     beforehand
    0.05
    ction
    0.05
     financially
    0.05
    ADED
    0.05
     sequentially
    0.05
    Activations Density 0.126%

    No Known Activations