© 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. 17-LLAMASCOPE-RES-131K
    11. 76079
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly focusing on terms related to women and men in sports contexts

    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
    (es
    -0.09
    aters
    -0.07
    er
    -0.07
    give
    -0.06
    emez
    -0.06
    inz
    -0.06
    duce
    -0.06
    olet
    -0.06
    olygon
    -0.06
    lets
    -0.06
    POSITIVE LOGITS
    folk
    0.08
    's
    0.08
    çļĦæĥħ
    0.07
    -only
    0.06
     loose
    0.06
    aña
    0.06
    ãĥ©ãĥ¼
    0.06
    andro
    0.06
    Ticker
    0.06
    ’s
    0.06
    Activations Density 0.012%

    No Known Activations