© 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. 68552
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting dates and date‐like expressions (e.g. month names, days, years, and “On <Month> <Day>, <Year>” constructions).

    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
    ＊
    -0.07
    istration
    -0.06
    Slider
    -0.06
    inating
    -0.06
     Ke
    -0.06
    úi
    -0.06
    ere
    -0.06
    [d
    -0.06
     Ever
    -0.06
    ())
↵
    -0.06
    POSITIVE LOGITS
    '(
    0.07
    Propagation
    0.07
    .Wait
    0.07
     jedn
    0.07
    δες
    0.07
    $fields
    0.06
    ジア
    0.06
    xmlns
    0.06
     ~/
    0.06
    {-
    0.06
    Activations Density 0.014%

    No Known Activations