© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 127105
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron responds to second-person pronouns and phrases directly addressing the reader (e.g. “you,” “your”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    instances of direct second-person address (words like "you" or "your" / sentences addressing the reader).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Gods
    -0.07
     EMPTY
    -0.07
    (Event
    -0.06
     possibilities
    -0.06
     Esper
    -0.06
     안
    -0.06
     waves
    -0.06
     città
    -0.06
     pairs
    -0.06
    :Array
    -0.06
    POSITIVE LOGITS
     наче
    0.07
    -contained
    0.07
    ęki
    0.07
     loneliness
    0.06
    iliki
    0.06
    받
    0.06
    цем
    0.06
    _MIC
    0.06
    breadcrumb
    0.06
    اورپ
    0.06
    Activations Density 0.188%

    No Known Activations