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. 130201
    Prev
    Next
    INDEX
    Explanations

    Professional advice and services

    np_max-act · gemini-2.0-flash

    The neuron fires on terms and short phrases that invoke professional expertise or advisory services, such as “expert guidance,” “professional consulting,” or “leveraging … expertise.”

    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
    """↵
    -0.07
    Gem
    -0.06
     DACA
    -0.06
    =value
    -0.06
    ."""
    -0.06
     spanking
    -0.06
     narrowly
    -0.06
     nowrap
    -0.06
    ції
    -0.06
    Exports
    -0.06
    POSITIVE LOGITS
     survivors
    0.07
     따른
    0.06
    (camera
    0.06
    шт
    0.06
    ارس
    0.06
    (low
    0.06
     innoc
    0.06
     нарез
    0.06
    ]==
    0.06
     диви
    0.06
    Activations Density 0.084%

    No Known Activations