© 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. 9-LLAMASCOPE-RES-131K
    11. 98908
    Prev
    Next
    INDEX
    Explanations

    references to UI components and their hierarchical structure in code

    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
    ↵
    -0.06
    heel
    -0.05
    asher
    -0.05
     subs
    -0.05
     str
    -0.05
     dismiss
    -0.05
     ta
    -0.05
     progn
    -0.05
     fro
    -0.05
     Hillary
    -0.05
    POSITIVE LOGITS
    ildo
    0.08
    ERGY
    0.08
    /antlr
    0.07
    angles
    0.07
    ıma
    0.07
    atinum
    0.07
    жениÑı
    0.07
    績
    0.07
    è¡Ľ
    0.07
    太éĥİ
    0.07
    Activations Density 0.020%

    No Known Activations