© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71545
    Prev
    Next
    INDEX
    Explanations

    references to government policies and healthcare-related financial implications

    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
     Seattle
    -0.08
    Seattle
    -0.08
     Tacoma
    -0.08
     Hayward
    -0.07
     Sacramento
    -0.07
     Pacific
    -0.07
    vore
    -0.07
     California
    -0.07
     Rajasthan
    -0.07
     Worcester
    -0.07
    POSITIVE LOGITS
     Kentucky
    0.18
     Louisville
    0.17
     KY
    0.15
    KY
    0.12
     Cincinnati
    0.12
     bourbon
    0.10
     Tennessee
    0.09
     Nashville
    0.09
     Bourbon
    0.09
    Louis
    0.09
    Activations Density 0.142%

    No Known Activations