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. 84453
    Prev
    Next
    INDEX
    Explanations

    court case dates

    np_max-act · gemini-2.0-flash

    The neuron detects numeric references to court filing metadata such as docket or case numbers and filing dates.

    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
     вред
    -0.06
    :d
    -0.06
    arak
    -0.06
     newspapers
    -0.06
    ك
    -0.05
     przed
    -0.05
    _[
    -0.05
     frustr
    -0.05
    зем
    -0.05
     Melissa
    -0.05
    POSITIVE LOGITS
    ۳۵
    0.08
     ULONG
    0.07
    (theme
    0.07
     CG
    0.07
    _listing
    0.07
     cà
    0.06
    	mkdir
    0.06
    _buttons
    0.06
     HB
    0.06
     cls
    0.06
    Activations Density 0.012%

    No Known Activations