© 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. 70861
    Prev
    Next
    INDEX
    Explanations

    instances of domestic abuse and violence

    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
    ezi
    -0.07
    werk
    -0.07
    èª
    -0.07
    remen
    -0.06
    ncy
    -0.06
    ypi
    -0.06
    uty
    -0.06
    æı¡
    -0.06
    ernen
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
     Domestic
    0.09
     domestic
    0.09
     physical
    0.09
     abusive
    0.08
    Dom
    0.08
     beat
    0.08
     abuse
    0.08
     household
    0.08
    .Dom
    0.07
     Physical
    0.07
    Activations Density 0.026%

    No Known Activations