© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that form mathematical inequality expressions (e.g. “|x−y|<b−a” or “ac<bd”).

    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
    Words
    -0.07
     процесс
    -0.07
     prospects
    -0.07
     consequences
    -0.07
     xuyên
    -0.07
     neuroscience
    -0.06
     Вы
    -0.06
    checksum
    -0.06
     Majority
    -0.06
     Pros
    -0.06
    POSITIVE LOGITS
     NONINFRINGEMENT
    0.06
    /gen
    0.06
    /loose
    0.06
    icies
    0.06
    _ER
    0.06
     کوچ
    0.06
     какой
    0.06
     immersive
    0.06
    وقت
    0.06
    ้าห
    0.06
    Activations Density 0.287%

    No Known Activations