Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5693
    Prev
    Next
    INDEX
    Explanations

    terms related to military personnel and their roles

    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
    imson
    -0.08
    大人
    -0.08
    ukt
    -0.08
    ukkan
    -0.08
    ieee
    -0.07
    raki
    -0.07
    neau
    -0.07
    umas
    -0.07
    utut
    -0.07
    æķĻæİĪ
    -0.07
    POSITIVE LOGITS
     corpor
    0.07
     mach
    0.07
     petty
    0.07
     helper
    0.06
     Petty
    0.06
    ÑĨеп
    0.06
     Mach
    0.06
     longevity
    0.06
    -
    0.06
     fore
    0.06
    Activations Density 0.023%

    No Known Activations