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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106294
    Prev
    Next
    INDEX
    Explanations

    references to medical personnel and emergency response training

    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
     Ernst
    -0.06
    egasus
    -0.06
    RAY
    -0.06
    ASCADE
    -0.06
    anje
    -0.06
    ìĭ¬
    -0.06
    ī
    -0.06
    Mapped
    -0.05
     Twe
    -0.05
    ERC
    -0.05
    POSITIVE LOGITS
    uset
    0.07
     kli
    0.06
    æ»
    0.06
     DISCLAIMER
    0.06
    chet
    0.06
     اÙĦÙĨÙĩ
    0.06
    _FS
    0.06
    swer
    0.06
    обов
    0.06
    |#
    0.06
    Activations Density 0.059%

    No Known Activations