© 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. 54334
    Prev
    Next
    INDEX
    Explanations

    library package

    np_max-act · gemini-2.0-flash

    commands related to manipulating Excel files in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds primarily to mentions of external Python library names.

    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
    Uvs
    -0.07
    amarin
    -0.06
     AGAIN
    -0.06
    VERIFY
    -0.06
    الى
    -0.06
    .Height
    -0.06
    Ball
    -0.06
     algunos
    -0.06
     застосування
    -0.06
     увер
    -0.06
    POSITIVE LOGITS
    (namespace
    0.07
     팬
    0.07
     Scanner
    0.06
     ach
    0.06
     sued
    0.06
     #(
    0.06
    added
    0.06
     appreh
    0.06
     Zombie
    0.06
    (description
    0.06
    Activations Density 0.013%

    No Known Activations