© 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. 56140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the search for or reference to a specific person's name

    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
    ucci
    -0.07
    ILI
    -0.06
    ili
    -0.06
     min
    -0.06
    committed
    -0.06
    cki
    -0.06
     survival
    -0.06
    ipheral
    -0.06
     mark
    -0.05
    ipt
    -0.05
    POSITIVE LOGITS
    -webpack
    0.07
    νÏĮ
    0.07
    íĬ
    0.07
    ofire
    0.06
    FindObject
    0.06
     Duy
    0.06
    atel
    0.06
    еÑĢÑĤи
    0.06
    174
    0.06
    (gcf
    0.06
    Activations Density 0.001%

    No Known Activations