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. 130466
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of formal patent background terms such as “technology” or “technique” in the text.

    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
     preceding
    -0.07
     crippling
    -0.06
    .biz
    -0.06
    нім
    -0.06
     Pars
    -0.06
    Rus
    -0.06
    descending
    -0.06
    Recording
    -0.06
    synthesize
    -0.06
    clicked
    -0.06
    POSITIVE LOGITS
    uchi
    0.06
     risk
    0.06
     Tôi
    0.06
    �
    0.06
    침
    0.06
     beneficiaries
    0.06
    情
    0.06
    zerbai
    0.06
     oranges
    0.06
    	username
    0.06
    Activations Density 0.006%

    No Known Activations