© 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. 59162
    Prev
    Next
    INDEX
    Explanations

    instances of formal events and their positive reception

    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
    angu
    -0.06
     Global
    -0.06
     daily
    -0.06
    .Today
    -0.06
    daily
    -0.06
    <-
    -0.06
     Manufact
    -0.05
     chilled
    -0.05
    agon
    -0.05
     global
    -0.05
    POSITIVE LOGITS
    izzo
    0.08
    ibel
    0.07
    ocene
    0.07
    /cms
    0.07
    pyx
    0.07
    tabla
    0.07
    ispers
    0.07
     Antar
    0.07
    chwitz
    0.07
    TeX
    0.07
    Activations Density 0.001%

    No Known Activations