© 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. 55516
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    This neuron detects the slash before and the first digits of a four-digit year in dates formatted like M/D/YYYY.

    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
    _precision
    -0.07
    	td
    -0.07
    <pre
    -0.07
     fün
    -0.06
    ầ
    -0.06
    _lim
    -0.06
     값
    -0.06
    _DEAD
    -0.06
    mia
    -0.06
     tä
    -0.06
    POSITIVE LOGITS
    ($('#
    0.08
     elim
    0.07
    jong
    0.07
     august
    0.07
     schools
    0.07
    models
    0.06
     энерг
    0.06
     червня
    0.06
     changing
    0.06
    _form
    0.06
    Activations Density 0.008%

    No Known Activations