© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16894
    Prev
    Next
    INDEX
    Explanations

    terms related to military units and formations

    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
    usercontent
    -0.08
    ÑģÑĭлки
    -0.08
     ENTITY
    -0.07
    ubar
    -0.07
    raki
    -0.07
    _RCC
    -0.07
    TEE
    -0.07
    #
    -0.07
    entities
    -0.07
    udes
    -0.07
    POSITIVE LOGITS
    qual
    0.07
    Globals
    0.06
     MPs
    0.06
    legen
    0.06
     units
    0.06
    ault
    0.06
    ive
    0.06
     Wellington
    0.06
    al
    0.06
    cre
    0.06
    Activations Density 0.021%

    No Known Activations