© 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. 15-LLAMASCOPE-RES-131K
    11. 294
    Prev
    Next
    INDEX
    Explanations

    references to coffee-related terms and brewing processes

    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
     Guth
    -0.07
    nid
    -0.06
    /movie
    -0.06
     Vac
    -0.06
    ìļ±
    -0.06
    ī´
    -0.06
    .mvp
    -0.06
    edula
    -0.06
    regor
    -0.06
    èİ
    -0.06
    POSITIVE LOGITS
    erator
    0.07
    zers
    0.07
    cura
    0.07
    εÏį
    0.07
    edom
    0.06
    essen
    0.06
    uada
    0.06
     ayn
    0.06
    æ¢ģ
    0.06
    ish
    0.06
    Activations Density 0.002%

    No Known Activations