© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53882
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to violent crime and murder investigations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Egg
    -0.07
    ساس
    -0.07
    ActionCreators
    -0.06
    ovna
    -0.06
    ฺ
    -0.06
    itore
    -0.06
    ENCIL
    -0.06
     ê¶ģ
    -0.06
    اÙĪÙĩ
    -0.06
     Shops
    -0.06
    POSITIVE LOGITS
     execution
    0.09
     Executes
    0.08
     bodies
    0.08
     executed
    0.07
     Execution
    0.07
     executions
    0.07
     Exec
    0.07
    -exec
    0.07
    execution
    0.07
    auer
    0.07
    Activations Density 0.029%

    No Known Activations