© 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. 89873
    Prev
    Next
    INDEX
    Explanations

    details about furniture or decorative items

    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
    elmet
    -0.07
    ree
    -0.06
     att
    -0.06
    omid
    -0.06
    Blocked
    -0.06
    adiator
    -0.06
    uit
    -0.06
     plaster
    -0.06
    dar
    -0.06
     balcon
    -0.06
    POSITIVE LOGITS
     table
    0.11
     tables
    0.10
     tabel
    0.09
    (table
    0.09
     TABLE
    0.08
    -table
    0.08
    .table
    0.08
     Table
    0.08
     Tables
    0.08
    	table
    0.08
    Activations Density 0.005%

    No Known Activations