© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 98757
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings and food experiences

    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
    uish
    -0.07
    ersist
    -0.07
    udden
    -0.06
     Boyle
    -0.06
     Federal
    -0.06
    inja
    -0.06
    ameda
    -0.06
     Awakening
    -0.06
    amed
    -0.06
    opher
    -0.05
    POSITIVE LOGITS
    .mixin
    0.07
     PROFITS
    0.07
     grop
    0.07
    ÑĥлÑı
    0.07
    ãĥ
    0.07
    âĻª
    0.06
    رÛĮ
    0.06
    _ASM
    0.06
    anax
    0.06
    uspend
    0.06
    Activations Density 0.029%

    No Known Activations