© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    situations involving teamwork or collaboration

    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
    .appspot
    -0.07
    _PATCH
    -0.07
    .Stack
    -0.07
     Gron
    -0.07
    çİĦ
    -0.07
    adio
    -0.06
     moda
    -0.06
    erchant
    -0.06
    atura
    -0.06
    idget
    -0.06
    POSITIVE LOGITS
     town
    0.07
    Äįku
    0.06
    Å¡ku
    0.06
    £½
    0.06
    adero
    0.06
     squ
    0.06
    VERTISE
    0.06
     Bas
    0.05
     post
    0.05
     deduct
    0.05
    Activations Density 0.027%

    No Known Activations