© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 96261
    Prev
    Next
    INDEX
    Explanations

    references to popular musicals or theatrical productions

    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
    onte
    -0.07
    deniz
    -0.07
    onym
    -0.06
    zell
    -0.06
    سÙĦ
    -0.06
    sein
    -0.06
    activex
    -0.06
    _href
    -0.06
     isolation
    -0.06
    иÑģк
    -0.06
    POSITIVE LOGITS
    hm
    0.07
    orks
    0.07
    affected
    0.06
    withstanding
    0.06
    prep
    0.06
     Tender
    0.06
    ews
    0.06
    238
    0.06
    ivas
    0.06
    ides
    0.06
    Activations Density 0.001%

    No Known Activations