© 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. 128564
    Prev
    Next
    INDEX
    Explanations

    phrases describing symptoms and medical conditions

    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
    ãĥ¼ãĤ
    -0.08
    δή
    -0.08
    ấn
    -0.07
    errated
    -0.07
    ÙĪار
    -0.07
    Interrupt
    -0.07
    idar
    -0.07
    pta
    -0.07
    .getSource
    -0.07
    ÃŃl
    -0.07
    POSITIVE LOGITS
     impending
    0.06
     synd
    0.06
     progress
    0.06
     signs
    0.06
     imminent
    0.06
     syndrome
    0.06
    akan
    0.06
     serious
    0.06
    687
    0.06
     advanced
    0.05
    Activations Density 0.010%

    No Known Activations