© 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. 17-LLAMASCOPE-RES-131K
    11. 29899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating timeframes and sequences related to 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
    ricks
    -0.07
    tps
    -0.07
    jang
    -0.06
    chap
    -0.06
    drs
    -0.06
    oure
    -0.06
    UiThread
    -0.06
    elib
    -0.06
    clin
    -0.06
    erras
    -0.06
    POSITIVE LOGITS
     hosting
    0.08
     tenant
    0.07
     use
    0.07
     Hosting
    0.07
     torrent
    0.06
     Tenant
    0.06
     tenants
    0.06
    ç§
    0.06
    emark
    0.06
    izio
    0.06
    Activations Density 0.034%

    No Known Activations