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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26682
    Prev
    Next
    INDEX
    Explanations

    programming terms and instructions related to configuration or customization

    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
    unday
    -0.07
    ole
    -0.06
     Niger
    -0.06
    302
    -0.06
    ild
    -0.06
    ents
    -0.06
    nam
    -0.06
    ramids
    -0.05
    rent
    -0.05
    our
    -0.05
    POSITIVE LOGITS
    (coder
    0.08
    _Customer
    0.07
    دÛĮد
    0.07
    /epl
    0.07
    ^K
    0.07
     esl
    0.07
    à¥Ĥà¤Ł
    0.07
    رÙĪج
    0.07
    _Variable
    0.07
    _RW
    0.07
    Activations Density 0.019%

    No Known Activations