© 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. 92238
    Prev
    Next
    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “date.”

    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
    877
    -0.08
     Gibbs
    -0.08
     Bull
    -0.07
     "../../../
    -0.07
     VII
    -0.07
    …I
    -0.07
     Gibson
    -0.07
     Hur
    -0.06
     Hill
    -0.06
     Barn
    -0.06
    POSITIVE LOGITS
     date
    0.12
    (date
    0.11
    date
    0.11
    startdate
    0.10
    Date
    0.10
    .Date
    0.10
    	date
    0.10
    [date
    0.10
    _date
    0.10
     dates
    0.10
    Activations Density 0.058%

    No Known Activations