© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65762
    Prev
    Next
    INDEX
    Explanations

    testimonials

    np_max-act · gemini-2.0-flash

    This neuron fires on words naming webpage sections or content blocks—e.g. “Portfolio,” “Testimonials,” “Case Studies”—i.e. section‐heading labels in a site structure.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    the structure and elements of a company website, particularly focusing on specific pages and sections that establish a clear online presence.

    oai_token-act-pair · gpt-4o-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
     Roots
    -0.07
    ulses
    -0.07
     hari
    -0.06
     darker
    -0.06
     stormed
    -0.06
     Current
    -0.06
    .loc
    -0.06
    Pair
    -0.06
     pf
    -0.06
    coe
    -0.06
    POSITIVE LOGITS
     testimonials
    0.11
    -render
    0.07
    ม
    0.07
     выдел
    0.07
     testimony
    0.07
     testimon
    0.07
    ۲۵
    0.07
    .internet
    0.06
    imonials
    0.06
    ОР
    0.06
    Activations Density 0.006%

    No Known Activations