Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84632
    Prev
    Next
    INDEX
    Explanations

    HTML form fields

    np_max-act · gemini-2.0-flash

    The neuron responds to form field attribute names and values (especially name= and id= in HTML form inputs and selects).

    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
    Bed
    -0.07
    ponsible
    -0.07
    _review
    -0.06
     الزر
    -0.06
    such
    -0.06
     river
    -0.06
    ("\"
    -0.06
    かに
    -0.06
     convinc
    -0.06
     hydr
    -0.06
    POSITIVE LOGITS
     threadIdx
    0.07
    populate
    0.06
    agrant
    0.06
    *L
    0.06
     pItem
    0.06
    >[
    0.06
     Calendar
    0.06
    uctive
    0.06
     ISSUE
    0.06
    .apiUrl
    0.06
    Activations Density 0.013%

    No Known Activations