© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56674
    Prev
    Next
    INDEX
    Explanations

    details related to payroll and employee benefits

    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
     Unblock
    -0.07
     Appalach
    -0.07
    _MR
    -0.07
     Surveillance
    -0.06
    даÑĤ
    -0.06
    çŃĨ
    -0.06
    ptom
    -0.06
    hardt
    -0.06
    uros
    -0.06
     EVT
    -0.06
    POSITIVE LOGITS
     payroll
    0.10
     hr
    0.07
    iro
    0.07
     HR
    0.07
    CompatActivity
    0.07
    odesk
    0.07
    idak
    0.06
    ©
    0.06
     overd
    0.06
     Wage
    0.06
    Activations Density 0.004%

    No Known Activations