© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers that include numeric digits (e.g. variable names like “u32Value”).

    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
     Berk
    -0.07
    iếng
    -0.07
     ارسال
    -0.07
     Crud
    -0.06
     Carr
    -0.06
    ابد
    -0.06
     peril
    -0.06
     blindly
    -0.06
    .words
    -0.06
    imální
    -0.06
    POSITIVE LOGITS
     Sultan
    0.07
     употреб
    0.06
     ธ
    0.06
    Unlike
    0.06
    efore
    0.06
     azt
    0.06
    likes
    0.06
     pleasant
    0.06
     unpleasant
    0.06
    ierge
    0.06
    Activations Density 0.032%

    No Known Activations