© 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. 9179
    Prev
    Next
    INDEX
    Explanations

    Coding questions/answers

    np_max-act · gemini-2.0-flash

    The neuron flags words and short phrases that signal a user’s question or request—e.g. “How,” “I,” “to,” “achieve,” “use,” etc.—essentially marking question/instruction language.

    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
    FORMAT
    -0.07
    vidence
    -0.06
    อลลาร
    -0.06
    ArrayOf
    -0.06
    ила
    -0.06
    �
    -0.06
    ibrated
    -0.06
    Evt
    -0.06
    Thu
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
     chopped
    0.07
     Μέ
    0.07
    -col
    0.07
    ＿＿＿＿＿＿＿＿
    0.07
     voor
    0.06
     &(
    0.06
     Apostle
    0.06
     çalışmalar
    0.06
    SceneManager
    0.06
     rencontr
    0.06
    Activations Density 0.048%

    No Known Activations