© 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. 17-LLAMASCOPE-RES-131K
    11. 72962
    Prev
    Next
    INDEX
    Explanations

    words related to dining and entertainment 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
    /etc
    -0.07
    èĦ
    -0.07
    quiv
    -0.06
     ÙĪغÙĬر
    -0.06
    ONGL
    -0.06
    353
    -0.06
    ษ
    -0.06
    ussen
    -0.06
    LETTE
    -0.06
     ãģĿãģ®ä»ĸ
    -0.06
    POSITIVE LOGITS
     Wayne
    0.06
     Vance
    0.06
    LOTS
    0.06
    ,strong
    0.06
     Rab
    0.06
    anks
    0.06
     anda
    0.06
    reds
    0.06
    r
    0.06
    foreground
    0.06
    Activations Density 0.038%

    No Known Activations