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. 130719
    Prev
    Next
    INDEX
    Explanations

    Dogs

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of dog breeds (e.g. “Pit Bull Terrier,” “Shih Tzu,” “dachshund,” “terrier,” etc.).

    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
    Dto
    -0.06
    .NUM
    -0.06
    محمد
    -0.06
     indust
    -0.06
    oren
    -0.06
    准
    -0.05
    บาง
    -0.05
     �
    -0.05
     pueblo
    -0.05
    แชม
    -0.05
    POSITIVE LOGITS
    _orders
    0.07
     yard
    0.07
    ût
    0.07
     Sq
    0.07
     fold
    0.06
     returned
    0.06
    .pages
    0.06
    Unix
    0.06
     tester
    0.06
    ран
    0.06
    Activations Density 0.017%

    No Known Activations