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. 130743
    Prev
    Next
    INDEX
    Explanations

    Writer

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of .NET resource-handling class names (e.g. “ResourceReader,” “ResourceWriter,” “TypeConverter,” etc.) in XML or code.

    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
     Specialty
    -0.07
    UTTON
    -0.07
    /Button
    -0.07
    Ty
    -0.06
    atabase
    -0.06
    파트
    -0.06
    iliate
    -0.06
    Changing
    -0.06
    499
    -0.06
    _entities
    -0.06
    POSITIVE LOGITS
     pubb
    0.07
     (!_
    0.07
    -start
    0.06
     �
    0.06
     md
    0.06
    stery
    0.06
     woven
    0.06
     merch
    0.06
     assures
    0.06
    еру
    0.06
    Activations Density 0.001%

    No Known Activations