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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90086
    Prev
    Next
    INDEX
    Explanations

    Flu shots/vaccinations

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to immunization or vaccination.

    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
     nutzen
    -0.06
    忍
    -0.06
     Пот
    -0.06
    笔
    -0.06
    .Mesh
    -0.06
    oise
    -0.06
     llevar
    -0.06
    Fine
    -0.06
    泉
    -0.06
    _FS
    -0.06
    POSITIVE LOGITS
    ussen
    0.07
     mandatory
    0.07
     vaccination
    0.07
     vaccinations
    0.06
    PLACE
    0.06
    unce
    0.06
    εί
    0.06
    Unauthorized
    0.06
     mín
    0.06
    ύ
    0.06
    Activations Density 0.014%

    No Known Activations