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. 85964
    Prev
    Next
    INDEX
    Explanations

    genetics and geography

    np_max-act · gemini-2.0-flash

    The neuron mainly detects numerical values and quantitative measurements (e.g. decimal numbers, statistics, and percentages) in scientific text.

    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
     Ung
    -0.06
     คำ
    -0.06
    あり
    -0.06
    Sz
    -0.06
     Happiness
    -0.06
    коз
    -0.06
    _deg
    -0.06
    xae
    -0.06
    igans
    -0.06
     aver
    -0.06
    POSITIVE LOGITS
    orses
    0.07
     duplicated
    0.07
     Doing
    0.07
    rací
    0.07
    .uid
    0.06
     resurgence
    0.06
     ac
    0.06
     Era
    0.06
    sumer
    0.06
    Contract
    0.06
    Activations Density 0.015%

    No Known Activations