© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29321
    Prev
    Next
    INDEX
    Explanations

    terms related to the impact of low oxygen levels on health

    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
    opleft
    -0.08
    æĩ
    -0.08
    ponsive
    -0.07
     bazen
    -0.07
    ίθ
    -0.07
    isor
    -0.07
    ilon
    -0.07
    beros
    -0.07
    uiltin
    -0.07
    æŁ»
    -0.07
    POSITIVE LOGITS
     soon
    0.08
     lack
    0.07
     rapidly
    0.07
     damage
    0.07
     loss
    0.07
     quickly
    0.06
     shortly
    0.06
    Soon
    0.06
    ult
    0.06
     surviv
    0.06
    Activations Density 0.003%

    No Known Activations