© 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. 72198
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and legal charges

    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
    bild
    -0.08
     arsch
    -0.07
    ryn
    -0.07
     Suspension
    -0.07
    ün
    -0.07
    oslav
    -0.07
     vý
    -0.07
    ispiel
    -0.07
    Äĩi
    -0.07
    ivor
    -0.07
    POSITIVE LOGITS
    0.07
    /rc
    0.06
     Elk
    0.06
     both
    0.06
    ishi
    0.06
     novelty
    0.06
    uron
    0.05
     gyro
    0.05
     copper
    0.05
    inx
    0.05
    Activations Density 0.023%

    No Known Activations