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. 93809
    Prev
    Next
    INDEX
    Explanations

    references to vaccine distribution and priority criteria

    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
    urgeon
    -0.08
    reten
    -0.07
    GMEM
    -0.07
    gaard
    -0.07
    ³
    -0.07
    adele
    -0.07
    Äŀ
    -0.07
    okt
    -0.07
    inesis
    -0.07
    _Lean
    -0.07
    POSITIVE LOGITS
     priority
    0.10
     Priority
    0.09
     
    0.09
    priority
    0.08
    Priority
    0.08
     priorit
    0.08
     category
    0.07
     age
    0.07
     first
    0.07
     phase
    0.07
    Activations Density 0.003%

    No Known Activations