© 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. 79040
    Prev
    Next
    INDEX
    Explanations

    references to bonuses and promotional incentives

    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
    tec
    -0.07
    ษ
    -0.07
    ÙĪدÛĮ
    -0.07
    ãģĵãĤį
    -0.07
    -quarters
    -0.07
    erken
    -0.07
    ahr
    -0.07
    awah
    -0.07
     meisten
    -0.07
    _logged
    -0.07
    POSITIVE LOGITS
    (es
    0.07
    /prom
    0.07
    aries
    0.07
    ware
    0.07
    iliary
    0.07
    TOTYPE
    0.07
    ocular
    0.06
    illac
    0.06
    oeff
    0.06
    ive
    0.06
    Activations Density 0.003%

    No Known Activations