© 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 EvalsExportsAPI 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. 71276
    Prev
    Next
    INDEX
    Explanations

    references to the challenges of modern life and busyness

    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
    umar
    -0.07
    kea
    -0.07
    uche
    -0.07
    /stdc
    -0.07
    olly
    -0.06
    icer
    -0.06
    nga
    -0.06
    inci
    -0.06
    stÅĻed
    -0.06
    å£
    -0.06
    POSITIVE LOGITS
    /bus
    0.11
     bus
    0.08
    busy
    0.08
    Busy
    0.08
     busy
    0.08
    Bus
    0.08
     BUS
    0.07
    _BUS
    0.07
     society
    0.07
     day
    0.07
    Activations Density 0.016%

    No Known Activations