© 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. 121379
    Prev
    Next
    INDEX
    Explanations

    descriptions of styles and qualities related to furniture and outdoor items

    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
    ë¦Ħ
    -0.08
    ework
    -0.08
    agli
    -0.07
    isNaN
    -0.07
    Ģ
    -0.07
     éģĵ
    -0.07
    ÄŁi
    -0.07
     ÙĨÛĮر
    -0.07
     bacheca
    -0.07
    _RESERVED
    -0.06
    POSITIVE LOGITS
    ima
    0.05
    ayah
    0.05
    Criterion
    0.05
     sport
    0.05
     alike
    0.05
     Bris
    0.05
    itol
    0.05
    &q
    0.05
     nhất
    0.05
     highest
    0.05
    Activations Density 0.005%

    No Known Activations