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. 130687
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on legal numerical references, such as docket numbers and case‐report citations.

    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
     Murdoch
    -0.06
    _zoom
    -0.06
     прест
    -0.06
    ,_
    -0.06
     Printf
    -0.06
    نية
    -0.06
    .Pull
    -0.06
    едагог
    -0.05
     appare
    -0.05
    -be
    -0.05
    POSITIVE LOGITS
    .rt
    0.07
    _hyper
    0.07
    ości
    0.07
     Surgical
    0.06
     Commentary
    0.06
     SO
    0.06
     caus
    0.06
     Dates
    0.06
    -pos
    0.06
     Đại
    0.06
    Activations Density 0.001%

    No Known Activations