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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129570
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron detects code patterns where a file is being opened (or created) for writing, i.e. use of the open(…) function with write mode.

    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
     IonicModule
    -0.07
    続
    -0.07
     всей
    -0.06
     footsteps
    -0.06
     Hamilton
    -0.06
     نگهد
    -0.06
    坚
    -0.06
     липня
    -0.06
     phương
    -0.06
     النس
    -0.06
    POSITIVE LOGITS
     κο
    0.07
     with
    0.06
    _sqrt
    0.06
     파일첨부
    0.06
    (mysql
    0.06
     [{"
    0.06
     initWith
    0.06
    __((
    0.06
    WITH
    0.06
    ้าม
    0.05
    Activations Density 0.043%

    No Known Activations