© 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. 82385
    Prev
    Next
    INDEX
    Explanations

    keywords related to places and items associated with comfort or home

    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
    naire
    -0.10
    edReader
    -0.09
    naires
    -0.09
    /or
    -0.09
    hips
    -0.09
    aires
    -0.08
    ment
    -0.08
    rophe
    -0.08
    osate
    -0.08
    itis
    -0.08
    POSITIVE LOGITS
    Ùij
    0.11
    ãĢħ
    0.10
    ri
    0.09
    Ùijا
    0.08
    à¹Ĩ
    0.08
     à¹Ĩ
    0.07
    emek
    0.07
    anzi
    0.07
    ترÛĮ
    0.07
    νÏĦ
    0.07
    Activations Density 0.085%

    No Known Activations