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. 130455
    Prev
    Next
    INDEX
    Explanations

    legal opinions and descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects legal citation elements such as case and docket numbers, section references, and other formal numeric identifiers.

    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
     děti
    -0.06
    FE
    -0.06
    غراف
    -0.06
    VP
    -0.06
    벤
    -0.06
     çalışma
    -0.06
     holding
    -0.06
     wur
    -0.06
    ців
    -0.06
    ITIZE
    -0.06
    POSITIVE LOGITS
     Smithsonian
    0.06
    (summary
    0.06
     прик
    0.06
    >Loading
    0.06
     Isaiah
    0.06
     screenHeight
    0.06
    .failure
    0.06
    	Boolean
    0.06
     diminish
    0.06
    کز
    0.06
    Activations Density 0.013%

    No Known Activations