© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73895
    Prev
    Next
    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash

    This neuron flags the beginnings of user or FAQ-style questions, especially lines that start with question words (Who, What, How, Can, Do, Is, Where, etc.) or end in a question mark.

    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
    domain
    -0.07
    .attributes
    -0.07
    clients
    -0.06
    (SP
    -0.06
    (plan
    -0.06
    wis
    -0.06
    (engine
    -0.06
    stations
    -0.06
    (tag
    -0.06
    ดย
    -0.06
    POSITIVE LOGITS
     nüfus
    0.08
     astounding
    0.07
    řila
    0.07
     nitel
    0.07
     συμπ
    0.07
     시스템
    0.07
    tığı
    0.07
     algún
    0.07
    /card
    0.06
     *)((
    0.06
    Activations Density 0.019%

    No Known Activations