© 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. 86401
    Prev
    Next
    INDEX
    Explanations

    topics related to sexual harassment and workplace misconduct

    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
    cstdint
    -0.07
     заÑĤ
    -0.07
    yte
    -0.07
    Uvs
    -0.07
    UTO
    -0.07
    åĿĤ
    -0.07
    rypto
    -0.07
    æ¨
    -0.07
    .Override
    -0.07
    acios
    -0.07
    POSITIVE LOGITS
     harassment
    0.11
     workplace
    0.10
     harass
    0.10
     sexual
    0.09
     Sexual
    0.09
     Workplace
    0.08
     harassed
    0.08
     conduct
    0.07
     workplaces
    0.07
    sexual
    0.07
    Activations Density 0.139%

    No Known Activations