© 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. 86981
    Prev
    Next
    INDEX
    Explanations

    topics related to workplace equity and discrimination issues

    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
    ÑģÑĤи
    -0.07
    pick
    -0.07
    APTER
    -0.07
    enville
    -0.07
    Pick
    -0.07
    itespace
    -0.07
    ivic
    -0.07
     اÙĦاØŃ
    -0.07
    loff
    -0.07
    steder
    -0.07
    POSITIVE LOGITS
     gender
    0.10
     equal
    0.09
     Gender
    0.09
    Gender
    0.09
     Equal
    0.08
     wage
    0.08
     male
    0.07
     Wage
    0.07
     salary
    0.07
     femin
    0.07
    Activations Density 0.002%

    No Known Activations