© 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. 116919
    Prev
    Next
    INDEX
    Explanations

    references to hate crimes and racist behavior

    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
    ckill
    -0.07
    лоп
    -0.07
    akedirs
    -0.07
    umper
    -0.07
    \Mapping
    -0.06
    .getStyle
    -0.06
    zp
    -0.06
    amate
    -0.06
    .VideoCapture
    -0.06
    rray
    -0.06
    POSITIVE LOGITS
    icot
    0.07
    ohl
    0.07
     Lime
    0.07
    IFA
    0.06
    rud
    0.06
    itty
    0.06
     epith
    0.06
    /tags
    0.06
    chimp
    0.06
     Freed
    0.06
    Activations Density 0.018%

    No Known Activations