© 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
    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. 55517
    Prev
    Next
    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on occurrences of the identifier “path” (e.g. require('path') or path.xxx), i.e. references to the file‐system path module or path operations.

    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
    rente
    -0.07
    ็นส
    -0.07
     ให
    -0.07
    ارش
    -0.07
    ่าต
    -0.07
    -danger
    -0.06
     Proud
    -0.06
    ونی
    -0.06
     NOAA
    -0.06
    _WAIT
    -0.06
    POSITIVE LOGITS
    amm
    0.07
     intrinsic
    0.07
    uibModal
    0.06
    path
    0.06
     日本
    0.06
    ้าง
    0.06
     назна
    0.06
     количе
    0.06
    objc
    0.06
     plagued
    0.06
    Activations Density 0.001%

    No Known Activations