Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130515
    Prev
    Next
    INDEX
    Explanations

    water, staying hydrated

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of hydration advice (drinking water, staying hydrated).

    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
    ادة
    -0.07
     ters
    -0.07
    ascar
    -0.06
    vinc
    -0.06
    \/
    -0.06
    赵
    -0.06
     воз
    -0.06
    locator
    -0.06
    chester
    -0.06
    เข
    -0.06
    POSITIVE LOGITS
    (evt
    0.07
     přesvěd
    0.07
     com
    0.07
     будинку
    0.07
    Suppress
    0.07
     upscale
    0.06
     Monthly
    0.06
    (full
    0.06
    	rep
    0.06
     FILE
    0.06
    Activations Density 0.007%

    No Known Activations