© 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. 71334
    Prev
    Next
    INDEX
    Explanations

    references to responsibilities and duties in a professional context

    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
    bers
    -0.08
    ania
    -0.07
    lied
    -0.06
    BERS
    -0.06
    gue
    -0.06
    ohn
    -0.06
    оÑıÑĤ
    -0.06
     stages
    -0.06
    acz
    -0.06
     ourselves
    -0.06
    POSITIVE LOGITS
     duties
    0.13
     job
    0.11
    ä»ķäºĭ
    0.11
     Dut
    0.10
     duty
    0.10
     office
    0.09
     Job
    0.09
     incumb
    0.09
    å·¥ä½ľ
    0.08
    -job
    0.08
    Activations Density 0.057%

    No Known Activations