© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39086
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens, especially multi‐digit numbers such as years, dates, counts, and percentages.

    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
    AQ
    -0.07
    kova
    -0.07
     freelance
    -0.07
     unborn
    -0.06
     ισχ
    -0.06
     Бор
    -0.06
    been
    -0.06
    滿
    -0.06
    iotic
    -0.06
     Nguyên
    -0.06
    POSITIVE LOGITS
     onClose
    0.07
     commod
    0.07
     accommod
    0.06
    ención
    0.06
    fade
    0.06
    itations
    0.06
     modifiers
    0.06
    imeter
    0.06
     modifier
    0.06
    	inst
    0.06
    Activations Density 0.027%

    No Known Activations