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

    Neuronpedia

    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. 74641
    Prev
    Next
    INDEX
    Explanations

    references to personal transformation and job-related 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
    Äįen
    -0.09
    ä¸įäºĨ
    -0.08
    legg
    -0.07
    agg
    -0.07
    enha
    -0.07
    eah
    -0.07
    rio
    -0.07
    ávÄĽ
    -0.07
    _INCLUDED
    -0.07
    .capture
    -0.07
    POSITIVE LOGITS
     sever
    0.09
     transition
    0.08
    transition
    0.08
     transitional
    0.07
     Transition
    0.07
     income
    0.07
     cushion
    0.07
     unemployment
    0.07
     financial
    0.06
     Income
    0.06
    Activations Density 0.006%

    No Known Activations