© 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. 17-LLAMASCOPE-RES-131K
    11. 77819
    Prev
    Next
    INDEX
    Explanations

    elements related to visual imagery or descriptions of artistic works

    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
    ÅĪ
    -0.07
    rowable
    -0.06
    .sharedInstance
    -0.06
    azar
    -0.06
    ahas
    -0.06
    िवर
    -0.06
     Kauf
    -0.06
    ilon
    -0.06
    caff
    -0.06
    uce
    -0.06
    POSITIVE LOGITS
     belong
    0.08
     belonged
    0.07
    zsche
    0.07
     belongs
    0.07
    oble
    0.07
    ä¾ĭ
    0.06
     fellow
    0.06
    ìĦł
    0.06
    izik
    0.06
    æĿ¥èĩª
    0.06
    Activations Density 0.031%

    No Known Activations