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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128702
    Prev
    Next
    INDEX
    Explanations

    references to the concept of work or employment

    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
    uling
    -0.07
    bery
    -0.07
    acent
    -0.07
    staking
    -0.07
    ioneer
    -0.07
    licit
    -0.07
    ä¹ī
    -0.07
    ÙĨز
    -0.06
    /fw
    -0.06
    elay
    -0.06
    POSITIVE LOGITS
    -class
    0.08
    -Class
    0.07
     Working
    0.07
     working
    0.07
    otos
    0.07
    bench
    0.07
    -working
    0.07
     stiff
    0.06
     hours
    0.06
    Working
    0.06
    Activations Density 0.019%

    No Known Activations