© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1155
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptors related to interior design and furniture functionality

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    åĿĬ
    -0.07
    sher
    -0.07
    nik
    -0.07
    oley
    -0.06
    lse
    -0.06
     ÙĨاØŃÛĮÙĩ
    -0.06
     Mansion
    -0.06
     Kamp
    -0.06
    aires
    -0.06
    yen
    -0.06
    POSITIVE LOGITS
     bedrooms
    0.07
     offices
    0.07
    icros
    0.07
     room
    0.07
     rooms
    0.07
    inar
    0.07
    753
    0.07
     mas
    0.07
    mas
    0.06
     Zucker
    0.06
    Activations Density 0.018%

    No Known Activations