© 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. 17-LLAMASCOPE-RES-131K
    11. 69897
    Prev
    Next
    INDEX
    Explanations

    references to festive or celebratory events

    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
    umbing
    -0.07
    ovice
    -0.07
    \grid
    -0.06
    strup
    -0.06
    auf
    -0.06
    ocket
    -0.06
    jiang
    -0.06
     japanese
    -0.06
    rone
    -0.06
     Greek
    -0.06
    POSITIVE LOGITS
     Irish
    0.17
     Ireland
    0.15
     Dublin
    0.13
     Celtic
    0.11
     Gael
    0.10
    reland
    0.10
     Guinness
    0.09
     Celt
    0.09
    elfast
    0.09
    Ir
    0.08
    Activations Density 0.034%

    No Known Activations