© 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. 95030
    Prev
    Next
    INDEX
    Explanations

    actions involving giving and receiving, as well as requests and commands

    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
     ?><?
    -0.09
    elper
    -0.07
    verity
    -0.07
     QLatin
    -0.07
    ιο
    -0.07
    ÛĮات
    -0.07
    rome
    -0.06
    بÛĮر
    -0.06
    ÙĪسط
    -0.06
    steller
    -0.06
    POSITIVE LOGITS
    oday
    0.07
    otal
    0.06
    ceased
    0.06
    è¡Ľ
    0.06
    CES
    0.06
     Formal
    0.06
    avid
    0.06
     formal
    0.06
    vik
    0.06
    ov
    0.06
    Activations Density 0.075%

    No Known Activations