© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108821
    Prev
    Next
    INDEX
    Explanations

    years and numerical data

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—especially years and other standalone numbers (and their punctuation).

    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
     wings
    -0.07
     Basics
    -0.06
     hunger
    -0.06
    illiseconds
    -0.06
     accidentally
    -0.06
     Cricket
    -0.06
    .Debugf
    -0.06
    (book
    -0.06
     AuthService
    -0.06
     Fayette
    -0.06
    POSITIVE LOGITS
     mlad
    0.08
    推荐
    0.06
    ательно
    0.06
    िसक
    0.06
    endum
    0.06
    евых
    0.06
    odont
    0.06
    ้อย
    0.06
     ترجم
    0.06
     �
    0.06
    Activations Density 0.041%

    No Known Activations