© 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. 118752
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bruce"

    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
    agle
    -0.07
     infix
    -0.07
    nes
    -0.07
     thù
    -0.07
    à¸
    -0.07
    staw
    -0.07
    ottes
    -0.07
    SingleNode
    -0.07
    eview
    -0.07
    ¥¿
    -0.07
    POSITIVE LOGITS
    yb
    0.08
    itect
    0.07
    y
    0.07
    umber
    0.07
     Almighty
    0.07
    enstein
    0.07
    erman
    0.07
    ETO
    0.06
    еÑĢо
    0.06
    uil
    0.06
    Activations Density 0.003%

    No Known Activations