© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126039
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace dynamics and negotiations

    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
    bjerg
    -0.08
    raç
    -0.07
    pron
    -0.07
    yles
    -0.07
     Creation
    -0.07
    gaard
    -0.07
    imler
    -0.07
    оÑĢÑĭ
    -0.07
    lectron
    -0.06
    заб
    -0.06
    POSITIVE LOGITS
     employers
    0.07
     salary
    0.07
     raises
    0.06
     HR
    0.06
     raise
    0.06
     employer
    0.06
    ASK
    0.06
    ItemSelected
    0.06
    ench
    0.06
     Salary
    0.06
    Activations Density 0.002%

    No Known Activations