© 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
    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. 110432
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    np_max-act · gemini-2.0-flash

    This neuron activates on code snippets that involve datetime operations—parsing dates, calling datetime.now(), and subtracting or computing differences between date/time values.

    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
    /plugin
    -0.07
    Detalle
    -0.06
     lieu
    -0.06
    來
    -0.06
    zipcode
    -0.06
    (/^
    -0.06
    paralle
    -0.06
    itin
    -0.06
    Modifier
    -0.06
    -submit
    -0.06
    POSITIVE LOGITS
     �
    0.06
     {$
    0.06
    voice
    0.06
     (?,
    0.06
     Fixes
    0.06
    .SelectedIndexChanged
    0.06
    (datas
    0.06
     grinned
    0.06
    تبار
    0.06
     intox
    0.06
    Activations Density 0.026%

    No Known Activations