© 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. 127163
    Prev
    Next
    INDEX
    Explanations

    28

    np_max-act · gemini-2.0-flash

    The neuron fires on standalone numeric tokens (especially those in the teens to low double digits) used as volume, issue, or page numbers in journal citation metadata.

    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
    quoted
    -0.06
     металли
    -0.06
    termination
    -0.06
     division
    -0.06
    ／
    -0.06
    _reader
    -0.06
     Php
    -0.06
     Razor
    -0.06
     والإ
    -0.05
    odies
    -0.05
    POSITIVE LOGITS
    力量
    0.07
    =:
    0.06
    ریم
    0.06
    ψε
    0.06
    /icon
    0.06
     nesta
    0.06
     رق
    0.06
    ocate
    0.06
    -pt
    0.06
    θλη
    0.06
    Activations Density 0.002%

    No Known Activations