© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41553
    Prev
    Next
    INDEX
    Explanations

    Date and time

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of date‐time parsing/formatting APIs (e.g. SimpleDateFormat, DateTimeFormatter, Joda-Time classes) in code.

    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
    От
    -0.09
     autor
    -0.07
    _patterns
    -0.07
     Password
    -0.07
    -0.06
     chants
    -0.06
    왕
    -0.06
     provincial
    -0.06
     partida
    -0.06
    複
    -0.06
    POSITIVE LOGITS
     hustle
    0.07
    )-(
    0.06
     Čer
    0.06
     meget
    0.06
    _STATIC
    0.06
    masked
    0.06
     meng
    0.06
     Spicer
    0.06
    .SaveChanges
    0.06
    sage
    0.06
    Activations Density 0.026%

    No Known Activations