© 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 EvalsExportsAPI 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. 85869
    Prev
    Next
    INDEX
    Explanations

    references to police actions and brutality in protest situations

    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
     Powered
    -0.07
    ARGER
    -0.07
     fitte
    -0.07
    orra
    -0.07
    ζα
    -0.07
    _locator
    -0.07
    æĪĺäºī
    -0.07
     architekt
    -0.07
    ruba
    -0.06
     ků
    -0.06
    POSITIVE LOGITS
     tear
    0.09
    deploy
    0.07
     police
    0.07
     crush
    0.07
     sweeps
    0.06
     Tear
    0.06
    hart
    0.06
     riot
    0.06
     deployed
    0.06
     suppress
    0.06
    Activations Density 0.040%

    No Known Activations