© 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. 22-LLAMASCOPE-RES-131K
    11. 4004
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues and the effects of lifestyle choices

    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
    ردÙĩ
    -0.08
    uhe
    -0.07
    (?:
    -0.07
    cko
    -0.07
    cke
    -0.07
     Siz
    -0.07
    .***.***
    -0.07
    _INITIALIZER
    -0.07
    ipher
    -0.06
    è¦
    -0.06
    POSITIVE LOGITS
     five
    0.09
     ten
    0.08
    five
    0.07
     cinco
    0.07
     fün
    0.07
     top
    0.07
     seven
    0.07
     пÑıÑĤÑĮ
    0.07
    äºĶ
    0.06
     three
    0.06
    Activations Density 0.009%

    No Known Activations