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. 40419
    Prev
    Next
    INDEX
    Explanations

    seeking medical attention

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens within advisory or instructional statements—especially health-care recommendations and directives (e.g., “you,” “should,” “contact,” “can,” etc.).

    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
     unions
    -0.07
     woll
    -0.07
    ebp
    -0.07
     إليه
    -0.07
     yapılması
    -0.06
    ريقة
    -0.06
    fg
    -0.06
    ijn
    -0.06
    双
    -0.06
    	connection
    -0.06
    POSITIVE LOGITS
    \
    0.07
    .Gradient
    0.07
     mosquito
    0.06
     releasing
    0.06
     Hose
    0.06
     läng
    0.06
    uyển
    0.06
     Dân
    0.06
     Previously
    0.06
     Humb
    0.06
    Activations Density 0.020%

    No Known Activations