© 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. 9449
    Prev
    Next
    INDEX
    Explanations

    information seeking

    np_max-act · gemini-2.0-flash

    This neuron fires on words indicating that the author has looked up or searched for a solution (e.g. “searching,” “searched,” “found,” “looking”).

    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
    Job
    -0.07
    erap
    -0.07
     cake
    -0.06
     करन
    -0.06
    servername
    -0.06
    board
    -0.06
    VIRTUAL
    -0.06
    calls
    -0.06
    cart
    -0.06
     modeling
    -0.06
    POSITIVE LOGITS
    らく
    0.07
     Eig
    0.06
    ./
    0.06
     eager
    0.06
    .Map
    0.06
     кос
    0.06
     культуры
    0.06
     blindly
    0.05
    localized
    0.05
    。在
    0.05
    Activations Density 0.048%

    No Known Activations