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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41153
    Prev
    Next
    INDEX
    Explanations

    .render

    np_max-act · gemini-2.0-flash

    requests for code and programming solutions.

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

    The neuron activates on occurrences of template‐rendering calls (e.g. “.render(”) in Jinja/Pyramid/Flask code.

    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
     tools
    -0.08
     gays
    -0.07
    \Auth
    -0.07
     barn
    -0.06
    022
    -0.06
     nodes
    -0.06
     pork
    -0.06
     cheese
    -0.06
    Data
    -0.06
    ола
    -0.06
    POSITIVE LOGITS
    ених
    0.08
    rejected
    0.07
     برگزار
    0.07
    prestashop
    0.06
     applauded
    0.06
    perhaps
    0.06
     orc
    0.06
     ребенка
    0.06
     endPoint
    0.06
     drafting
    0.06
    Activations Density 0.001%

    No Known Activations