© 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. 93685
    Prev
    Next
    INDEX
    Explanations

    .compile

    np_max-act · gemini-2.0-flash

    The neuron fires on uses of the word “compile” (especially the Keras/TensorFlow model.compile calls) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Python code related to deep learning models.

    oai_token-act-pair · gpt-4o-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
     Erg
    -0.07
     Polynomial
    -0.07
    OPY
    -0.06
     베
    -0.06
     donne
    -0.06
    nej
    -0.06
     hypothesis
    -0.06
    егра
    -0.06
     tane
    -0.06
    ito
    -0.06
    POSITIVE LOGITS
    .compile
    0.07
    .render
    0.07
     Delete
    0.07
     dedim
    0.06
    querySelector
    0.06
     Shall
    0.06
    】,【
    0.06
     Valor
    0.06
     Chatt
    0.06
     рез
    0.06
    Activations Density 0.000%

    No Known Activations