© 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. 118951
    Prev
    Next
    INDEX
    Explanations

    terms related to medical symptoms and 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
    thest
    -0.08
    apses
    -0.08
    à¹Ĩ
    -0.07
    uke
    -0.07
    itore
    -0.07
    é¾Ħ
    -0.07
    éŀ
    -0.07
    име
    -0.07
    apore
    -0.07
    ι
    -0.07
    POSITIVE LOGITS
     breath
    0.09
     breathing
    0.09
     gas
    0.08
     breathe
    0.08
     Breath
    0.07
     oxygen
    0.07
     respir
    0.07
    bre
    0.06
     breathed
    0.06
     Oxygen
    0.06
    Activations Density 0.002%

    No Known Activations