© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89896
    Prev
    Next
    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    This neuron detects when the text is about passing or displaying a personalized welcome message (e.g. “Hello, Craig!”) to a user in a view.

    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
     warns
    -0.07
    Group
    -0.07
     público
    -0.07
    너
    -0.06
    Streams
    -0.06
    Girls
    -0.06
    晶
    -0.06
    isspace
    -0.06
     Iris
    -0.06
     dalam
    -0.06
    POSITIVE LOGITS
    educt
    0.06
     vulner
    0.06
     添加
    0.06
     Exhaust
    0.06
    기에
    0.06
     fencing
    0.06
     자기
    0.06
     than
    0.06
    atalog
    0.06
     thoughtful
    0.06
    Activations Density 0.136%

    No Known Activations