© 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. 5298
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to criminal behavior and societal issues

    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
    bridge
    -0.07
    ylland
    -0.07
     InitializeComponent
    -0.07
     arada
    -0.07
    ÙĪاÙĩ
    -0.07
    ataire
    -0.07
    Orm
    -0.07
    aben
    -0.06
    odef
    -0.06
     öden
    -0.06
    POSITIVE LOGITS
    itch
    0.07
    0.07
     Ask
    0.06
    appa
    0.06
    ycop
    0.06
    ires
    0.06
     took
    0.06
     suggest
    0.06
     vault
    0.06
    vert
    0.06
    Activations Density 0.037%

    No Known Activations