© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7789
    Prev
    Next
    INDEX
    Explanations

    estradiol

    np_max-act · gemini-2.0-flash

    This neuron detects references to the hormone 17β-estradiol (the “17 beta-estradiol” sequence).

    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
    607
    -0.07
     Поч
    -0.07
    طور
    -0.07
    890
    -0.07
     boys
    -0.07
    avigate
    -0.07
     Cut
    -0.06
     Child
    -0.06
    "F
    -0.06
    “No
    -0.06
    POSITIVE LOGITS
    ладу
    0.06
    итай
    0.06
     prav
    0.06
     lowes
    0.06
     también
    0.06
    afka
    0.06
    辑
    0.06
    žitě
    0.06
    из
    0.06
     robbed
    0.06
    Activations Density 0.007%

    No Known Activations