© 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. 9-LLAMASCOPE-RES-131K
    11. 96752
    Prev
    Next
    INDEX
    Explanations

    references to Oktoberfest and related celebrations

    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
    гл
    -0.08
    setLayout
    -0.07
    rang
    -0.07
     Liberties
    -0.06
    antal
    -0.06
     kad
    -0.06
    rych
    -0.06
    ewater
    -0.06
    ushman
    -0.06
    è·
    -0.06
    POSITIVE LOGITS
    /cop
    0.07
    simd
    0.06
    eder
    0.06
     Cop
    0.06
     zel
    0.06
    ory
    0.06
    -style
    0.06
    sti
    0.06
     cop
    0.06
     quoi
    0.06
    Activations Density 0.002%

    No Known Activations