© 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. 62473
    Prev
    Next
    INDEX
    Explanations

    references to military units and their designations

    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
    rana
    -0.07
    بÙĬر
    -0.07
    ió
    -0.07
    ζί
    -0.07
    ARAM
    -0.06
    enha
    -0.06
    goto
    -0.06
    ilen
    -0.06
    Æ°á»Ľ
    -0.06
    Spacer
    -0.06
    POSITIVE LOGITS
    :animated
    0.07
    -unstyled
    0.06
    ฯ
    0.06
    isms
    0.06
    ive
    0.06
    /browse
    0.06
    æ°ı
    0.06
    IBUTE
    0.06
     moments
    0.06
    aurus
    0.06
    Activations Density 0.012%

    No Known Activations