© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89122
    Prev
    Next
    INDEX
    Explanations

    URLs and routing

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of URL‐generation calls or tags (e.g. “url_for” in Flask or “{% url … %}” in Django templates).

    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
     TZ
    -0.07
    igor
    -0.07
     Mand
    -0.07
     Estate
    -0.06
     doe
    -0.06
     Get
    -0.06
    GBK
    -0.06
    -old
    -0.06
     ย
    -0.06
     Rox
    -0.06
    POSITIVE LOGITS
    �택
    0.07
    �
    0.07
    athroom
    0.06
    HideInInspector
    0.06
    .gridColumn
    0.06
    ụp
    0.06
     attendance
    0.06
    ิ่
    0.06
     brewed
    0.06
     actionTypes
    0.06
    Activations Density 0.008%

    No Known Activations