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. 85854
    Prev
    Next
    INDEX
    Explanations

    returning applications/forms

    np_max-act · gemini-2.0-flash

    The neuron fires on instructions telling the reader to return or submit a form or document (e.g. “return it to…,” “submit your application,” “returned in person or mailed”).

    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
    .csrf
    -0.07
     Mur
    -0.06
    RB
    -0.06
     bh
    -0.06
     plate
    -0.06
    Brains
    -0.06
    plate
    -0.06
    atically
    -0.06
     Calder
    -0.06
     Ric
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    _IDX
    0.06
     دادن
    0.06
     Προ
    0.06
     ilet
    0.06
     přisp
    0.06
     προ
    0.06
     Ottawa
    0.06
     Mayıs
    0.06
    .Photo
    0.06
    Activations Density 0.015%

    No Known Activations