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

    Neuronpedia

    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. 17040
    Prev
    Next
    INDEX
    Explanations

    references to diabetes and its associated challenges

    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
    æķ¬
    -0.07
    à¹ģà¸Ħ
    -0.07
     Ã¶ÄŁ
    -0.07
    ALK
    -0.07
    nap
    -0.06
    .vars
    -0.06
    -ce
    -0.06
     ÃĩalÄ±ÅŁ
    -0.06
    SizeMode
    -0.06
    Recovered
    -0.06
    POSITIVE LOGITS
     diabetic
    0.07
     Diabetes
    0.07
     ABI
    0.07
     diabetes
    0.07
    _UNDEFINED
    0.06
     Khu
    0.06
     insulin
    0.06
     absent
    0.06
     Ging
    0.06
    ocop
    0.06
    Activations Density 0.003%

    No Known Activations