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. 130229
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    This neuron detects XML structural tokens—particularly opening tag markers, tag names, and namespace/schema attributes—in Maven POM files.

    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
    Tank
    -0.06
    они
    -0.06
    기준
    -0.06
    601
    -0.06
     招
    -0.06
    SocketAddress
    -0.06
    697
    -0.06
     perception
    -0.06
    Prototype
    -0.06
    goals
    -0.06
    POSITIVE LOGITS
     entwick
    0.07
    =utf
    0.07
     translating
    0.07
     alcan
    0.06
    -post
    0.06
     belirtilen
    0.06
    uyển
    0.06
     Throws
    0.06
     sidl
    0.06
    JB
    0.06
    Activations Density 0.002%

    No Known Activations