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. 40415
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron detects the leading asterisk tokens used in multi‐line (docblock) comment lines.

    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
    -follow
    -0.06
     poised
    -0.06
    textures
    -0.06
     STOCK
    -0.06
     Моск
    -0.06
    ียงใหม
    -0.06
     Укра
    -0.06
    ско
    -0.06
     खतर
    -0.06
    POL
    -0.06
    POSITIVE LOGITS
    ۲۳
    0.07
    _blog
    0.06
    ivors
    0.06
    branches
    0.06
    email
    0.06
    $results
    0.06
    .ret
    0.06
    (db
    0.06
     gdk
    0.06
    .getTime
    0.06
    Activations Density 0.001%

    No Known Activations