© 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. 106588
    Prev
    Next
    INDEX
    Explanations

    words related to life and living beings

    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
    utsch
    -0.08
    .lv
    -0.08
    acas
    -0.07
    ocup
    -0.07
    remium
    -0.07
    iae
    -0.07
    ystack
    -0.07
    ầu
    -0.07
    obao
    -0.07
    utely
    -0.07
    POSITIVE LOGITS
     life
    0.07
    /live
    0.06
     quarters
    0.06
    опиÑģ
    0.06
    ocha
    0.06
     expectancy
    0.06
    rink
    0.06
     tren
    0.06
    ramento
    0.05
    -threatening
    0.05
    Activations Density 0.006%

    No Known Activations