© 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. 83781
    Prev
    Next
    INDEX
    Explanations

    references to military service and war experiences

    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
    Summon
    -0.06
    ero
    -0.06
    eros
    -0.06
    yd
    -0.06
    師
    -0.06
    ãģ£ãģ¡
    -0.06
    еÑģÑĤо
    -0.06
    Hosting
    -0.06
     susp
    -0.06
     cruise
    -0.06
    POSITIVE LOGITS
     civilian
    0.10
     hometown
    0.08
     discharge
    0.08
     post
    0.08
     discharged
    0.08
     civilians
    0.07
    Wunused
    0.07
    çķ
    0.07
    /WebAPI
    0.07
     deser
    0.07
    Activations Density 0.017%

    No Known Activations