© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85673
    Prev
    Next
    INDEX
    Explanations

    .writer

    np_max-act · gemini-2.0-flash

    This neuron detects the creation or use of a CSV writer in Python code (e.g. calls to csv.writer and related writerow/writerows methods).

    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
     dört
    -0.07
     Başkan
    -0.06
    adier
    -0.06
    č
    -0.06
    sında
    -0.06
    �
    -0.06
    (fl
    -0.06
    _bt
    -0.06
    相
    -0.06
     oldest
    -0.06
    POSITIVE LOGITS
    .writer
    0.07
    _begin
    0.06
    арамет
    0.06
     вип
    0.06
    RAND
    0.06
    asctime
    0.06
    ност
    0.06
     метод
    0.06
    (unit
    0.06
    inator
    0.06
    Activations Density 0.000%

    No Known Activations