© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 42341
    Prev
    Next
    INDEX
    Explanations

    categories and indicators related to family structures and social demographics

    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
    port
    -0.06
     La
    -0.06
     coc
    -0.06
    onya
    -0.05
    363
    -0.05
    asa
    -0.05
     running
    -0.05
    itto
    -0.05
    uko
    -0.05
    ikal
    -0.05
    POSITIVE LOGITS
    оÑĢаз
    0.08
    Tween
    0.08
    ÄĽÅ¾
    0.08
    ctal
    0.08
    phans
    0.07
    META
    0.07
    à¥ģस
    0.07
     binh
    0.07
    ùi
    0.07
    ÙĦ
    0.07
    Activations Density 0.007%

    No Known Activations