© 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. 126756
    Prev
    Next
    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash

    The neuron fires on code‐related tokens, especially those having to do with SQL query execution and parameterized queries (e.g. “execute,” “parameterized,” “prepared,” “SQL,” etc.).

    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
    092
    -0.06
     /\.
    -0.06
     Peninsula
    -0.06
    .reference
    -0.06
    genic
    -0.06
    -primary
    -0.06
    owe
    -0.06
     ز
    -0.06
    DropDown
    -0.06
     chatt
    -0.06
    POSITIVE LOGITS
    (torch
    0.08
    ultimate
    0.06
     carrots
    0.06
     LoggerFactory
    0.06
    (Arrays
    0.06
     распростран
    0.06
    ($"{
    0.06
    523
    0.06
     importante
    0.06
     SharePoint
    0.06
    Activations Density 0.010%

    No Known Activations