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

    Neuronpedia

    Jacobian LensNEW
    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. 57345
    Prev
    Next
    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    This neuron flags the informal answerer's commentary in responses—words like “I’ve,” “safe,” “true,” and similar personal or evaluative terms used when explaining or qualifying an answer.

    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
    ricao
    -0.07
    ัญญ
    -0.07
    ertino
    -0.06
    ilename
    -0.06
    iao
    -0.06
    Installation
    -0.06
     trữ
    -0.06
    ＿＿
    -0.06
    .dependencies
    -0.06
    iệu
    -0.06
    POSITIVE LOGITS
    Š
    0.06
     servlet
    0.06
     nid
    0.06
    .maxLength
    0.06
     luật
    0.06
     outliers
    0.06
     Juli
    0.06
     �
    0.06
     �
    0.06
    φέ
    0.06
    Activations Density 0.217%

    No Known Activations