© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    references to significant and violent events or crimes

    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
    ssue
    -0.07
    oop
    -0.07
    722
    -0.06
     é»
    -0.06
    orest
    -0.06
    erland
    -0.06
    emme
    -0.06
    ler
    -0.06
    UMP
    -0.06
    ugu
    -0.06
    POSITIVE LOGITS
    icz
    0.09
     plein
    0.06
    udev
    0.06
     meiden
    0.06
     Olympic
    0.06
    ussen
    0.06
    readcr
    0.06
    alic
    0.06
    SectionsIn
    0.06
    ResourceManager
    0.06
    Activations Density 0.001%

    No Known Activations