© 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. 76802
    Prev
    Next
    INDEX
    Explanations

    terms related to acute 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
    ERY
    -0.07
    æ»
    -0.07
     Meer
    -0.07
    ahlen
    -0.07
    osite
    -0.07
    _MODULE
    -0.07
    ying
    -0.07
    hma
    -0.07
     æ»
    -0.07
    roll
    -0.07
    POSITIVE LOGITS
    anche
    0.09
    aneous
    0.07
    anches
    0.07
     Ra
    0.07
    /sub
    0.06
     polymer
    0.06
     labore
    0.06
    oppers
    0.06
    rome
    0.06
     pancre
    0.06
    Activations Density 0.010%

    No Known Activations