© 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. 15492
    Prev
    Next
    INDEX
    Explanations

    terms that indicate regular participation or attendance in events or activities

    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
    ensa
    -0.07
    oul
    -0.07
    426
    -0.07
    ovich
    -0.07
    uais
    -0.07
    ilip
    -0.06
    ories
    -0.06
    hea
    -0.06
     Äiju
    -0.06
    ournals
    -0.06
    POSITIVE LOGITS
     fixture
    0.09
     fixtures
    0.09
     presence
    0.07
     frequent
    0.07
    fixture
    0.07
     regular
    0.07
     haunt
    0.07
     Hab
    0.07
    elper
    0.06
     coun
    0.06
    Activations Density 0.013%

    No Known Activations