© 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. 56552
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-employment and personal responsibility in work

    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
    viso
    -0.07
    lider
    -0.07
    اÙħÙĬ
    -0.07
    ective
    -0.07
    ampions
    -0.07
    elib
    -0.07
    âl
    -0.07
    ectl
    -0.07
    onis
    -0.07
    vio
    -0.07
    POSITIVE LOGITS
     independent
    0.07
     independence
    0.07
    -independent
    0.07
     Supplies
    0.07
     Independent
    0.07
     independently
    0.06
     fluct
    0.06
     Ava
    0.06
    Independent
    0.06
    çģµ
    0.06
    Activations Density 0.004%

    No Known Activations