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. 40615
    Prev
    Next
    INDEX
    Explanations

    File operations in code

    np_max-act · gemini-2.0-flash

    This neuron detects references to a file object (the “f” handle) in Python `with open(...) as f:` blocks.

    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
    .memo
    -0.07
    masını
    -0.07
    舰
    -0.07
     عشق
    -0.06
     Optimization
    -0.06
     полот
    -0.06
     colormap
    -0.06
    Leo
    -0.06
     telefone
    -0.06
    nod
    -0.06
    POSITIVE LOGITS
     testimonials
    0.07
     επι
    0.07
     decl
    0.07
     Venezuelan
    0.06
     justice
    0.06
     stere
    0.06
     declines
    0.06
     rumors
    0.06
     imposs
    0.06
     Announcement
    0.06
    Activations Density 0.002%

    No Known Activations