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. 104115
    Prev
    Next
    INDEX
    Explanations

    configurable options

    np_max-act · gemini-2.0-flash

    information related to advanced technologies and innovative features in consumer products.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to technical specification details—especially numeric measurements, units, and configurable settings—in product descriptions.

    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
    ج
    -0.07
     Faster
    -0.06
    寻
    -0.06
     Employee
    -0.06
     headphones
    -0.06
     sort
    -0.06
     comprend
    -0.06
     vực
    -0.06
    elm
    -0.06
    стр
    -0.06
    POSITIVE LOGITS
    sanız
    0.07
     Charging
    0.07
    [,
    0.06
    <ll
    0.06
    '>
    0.06
    하며
    0.06
     Responses
    0.06
     ovšem
    0.06
    ारत
    0.06
     Rounded
    0.06
    Activations Density 0.037%

    No Known Activations