© 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. 61070
    Prev
    Next
    INDEX
    Explanations

    function declarations and method signatures in code

    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
     Malone
    -0.07
    _LOADING
    -0.06
     поÑĪ
    -0.06
     Went
    -0.06
     indifferent
    -0.06
    ÙĪاء
    -0.06
    createClass
    -0.06
    oders
    -0.06
    unta
    -0.06
    ikhail
    -0.05
    POSITIVE LOGITS
     return
    0.08
    {return
    0.07
    aunch
    0.07
    return
    0.07
    Bad
    0.06
    ciler
    0.06
    BAD
    0.06
    á»Ŀ
    0.06
    ards
    0.06
    	return
    0.06
    Activations Density 0.009%

    No Known Activations