© 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. 15-LLAMASCOPE-RES-131K
    11. 86567
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of authority or their interactions with various 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
    adero
    -0.07
    ensa
    -0.06
    ioc
    -0.06
    алÑİ
    -0.06
    olare
    -0.06
     gew
    -0.06
    تÙĪر
    -0.06
    quete
    -0.06
    als
    -0.06
    .runtime
    -0.06
    POSITIVE LOGITS
     countless
    0.08
    abus
    0.07
     multitude
    0.06
    ushman
    0.06
    akh
    0.06
    ÙĦÙĤ
    0.06
     neglig
    0.06
    809
    0.06
     paycheck
    0.06
     myriad
    0.06
    Activations Density 0.029%

    No Known Activations