© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89889
    Prev
    Next
    INDEX
    Explanations

    themes related to gender differences and feminism

    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
    ModelState
    -0.07
    spd
    -0.07
    opal
    -0.07
    ationship
    -0.06
    loff
    -0.06
    aub
    -0.06
    rary
    -0.06
    aja
    -0.06
    .ro
    -0.06
    reso
    -0.06
    POSITIVE LOGITS
     differences
    0.07
     Differences
    0.07
    æ³
    0.07
    å·®
    0.06
     roles
    0.06
    ysters
    0.06
    ãģĤãĤĬ
    0.06
    .chars
    0.06
    Quotes
    0.06
     complimentary
    0.06
    Activations Density 0.006%

    No Known Activations