© 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. 127540
    Prev
    Next
    INDEX
    Explanations

    features related to architectural layouts and open floor plans in homes

    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
    باÙĨ
    -0.07
    .toolbox
    -0.07
    /assert
    -0.06
    robe
    -0.06
     lim
    -0.06
    éŨ
    -0.06
    lim
    -0.06
    ¶Į
    -0.06
     resource
    -0.06
    á¿Ĩ
    -0.06
    POSITIVE LOGITS
    å¼ı
    0.08
     layout
    0.08
    porn
    0.08
    atted
    0.07
    layout
    0.07
     living
    0.07
    å¡
    0.07
     interim
    0.07
     Layout
    0.07
    _Style
    0.06
    Activations Density 0.005%

    No Known Activations