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. 40583
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    XML tags and attributes typically used in software localization and resource files.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on XML namespace declarations (xmlns attributes and their “names” tokens).

    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
    ENCED
    -0.07
     Husband
    -0.06
     Fold
    -0.06
     bathtub
    -0.06
     Leslie
    -0.06
    -д
    -0.06
    _pushButton
    -0.06
    руют
    -0.06
     товарів
    -0.06
     Keep
    -0.06
    POSITIVE LOGITS
    MLS
    0.07
    bau
    0.07
    inion
    0.06
    _PRIVATE
    0.06
    ]]
    ↵
    0.06
     |=
    0.06
    (define
    0.06
     <=>
    0.06
     OpenSSL
    0.06
    ional
    0.06
    Activations Density 0.001%

    No Known Activations