© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106992
    Prev
    Next
    INDEX
    Explanations

    references to military titles and ranks

    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
    ertino
    -0.08
    ạn
    -0.07
    ultz
    -0.07
    zı
    -0.07
    ristol
    -0.07
    sburg
    -0.07
    readcr
    -0.07
    ocz
    -0.07
    mom
    -0.07
    uzzi
    -0.07
    POSITIVE LOGITS
    wards
    0.07
    wick
    0.06
    _CPP
    0.06
    193
    0.06
    ys
    0.06
    .AWS
    0.06
     bo
    0.05
    JR
    0.05
     blown
    0.05
     Inventory
    0.05
    Activations Density 0.000%

    No Known Activations