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. 130459
    Prev
    Next
    INDEX
    Explanations

    quotes from people

    np_max-act · gemini-2.0-flash

    The neuron fires on speaker‐attribution and expert‐quote markers—words like “says,” “reports,” and named credentials (e.g. “MD,” “PhD,” or expert names) that introduce a quoted opinion.

    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
     glued
    -0.07
     definition
    -0.07
    ]])↵
    -0.06
     posed
    -0.06
     rectangles
    -0.06
     crying
    -0.06
     south
    -0.06
    ISTORY
    -0.06
     crank
    -0.06
    aments
    -0.06
    POSITIVE LOGITS
    otten
    0.07
     Γου
    0.07
    IntegerField
    0.06
    emotion
    0.06
    .Live
    0.06
    ItemSelectedListener
    0.06
    dbuf
    0.06
     Kavanaugh
    0.06
     Firestore
    0.06
     THB
    0.06
    Activations Density 0.039%

    No Known Activations