© 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. 41030
    Prev
    Next
    INDEX
    Explanations

    features related to museums, specifically open-air living museums

    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
     kys
    -0.07
    ØŃÙĦ
    -0.06
    æ¨ĵ
    -0.06
    é«ĺçŃī
    -0.06
    ocup
    -0.06
    ีà¹Ģà¸Ń
    -0.06
    浦
    -0.06
    кÑĤа
    -0.06
     seconds
    -0.06
    ÑĥлÑİ
    -0.06
    POSITIVE LOGITS
    htdocs
    0.07
     auth
    0.07
     authenticity
    0.07
    rep
    0.07
     recreated
    0.07
    /theme
    0.07
     model
    0.07
     museum
    0.07
    _rep
    0.06
     site
    0.06
    Activations Density 0.023%

    No Known Activations