© 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. 91429
    Prev
    Next
    INDEX
    Explanations

    pandas library

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the pandas `drop()` method call (e.g. “drop(…)”) used to remove columns or rows from a DataFrame.

    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
     кла
    -0.07
    Fil
    -0.07
    ož
    -0.06
     nationality
    -0.06
    :length
    -0.06
     Metal
    -0.06
    _logical
    -0.06
    ẳ
    -0.06
     getY
    -0.06
     emitter
    -0.06
    POSITIVE LOGITS
    _not
    0.06
    lli
    0.06
    HeaderView
    0.06
    _periods
    0.06
    RCT
    0.06
    만남
    0.06
    izz
    0.06
    ζα
    0.06
     StreamLazy
    0.06
     nhắc
    0.06
    Activations Density 0.010%

    No Known Activations