Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130189
    Prev
    Next
    INDEX
    Explanations

    sys

    np_max-act · gemini-2.0-flash

    This neuron detects references to Python’s filesystem paths—especially use of sys.path, os.path, and related calls that retrieve the interpreter or module search directories.

    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
     Mountain
    -0.07
    uffled
    -0.07
    _bad
    -0.06
    ीट
    -0.06
     ні
    -0.06
    OUN
    -0.06
    trash
    -0.06
    04
    -0.06
     плен
    -0.06
    Nice
    -0.06
    POSITIVE LOGITS
    (sys
    0.08
     xuyên
    0.08
    577
    0.07
    /UIKit
    0.06
     getSource
    0.06
     Fir
    0.06
    .
    0.06
     syrup
    0.06
     onClick
    0.06
    .volley
    0.06
    Activations Density 0.002%

    No Known Activations