© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125045
    Prev
    Next
    INDEX
    Explanations

    alanine aminotransferase

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of enzyme‐based medical test names—especially liver function enzymes (e.g. ALT, AST, GGT) ending in “‐ase.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prescription
    -0.08
     BF
    -0.07
    [ind
    -0.07
    \Data
    -0.07
     kapı
    -0.07
     Windows
    -0.07
     Entries
    -0.07
    rozen
    -0.06
    observeOn
    -0.06
     Bearing
    -0.06
    POSITIVE LOGITS
     Be
    0.07
     guard
    0.06
     might
    0.06
    strument
    0.06
    paused
    0.06
     unicorn
    0.06
     dentist
    0.06
     Au
    0.06
     surgeon
    0.06
    祖
    0.06
    Activations Density 0.001%

    No Known Activations