© 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. 74891
    Prev
    Next
    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash

    the opening of procedural/code blocks in hardware description language snippets (e.g., starts of “begin … end” sections).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ioni
    -0.07
     bekannt
    -0.07
     한번
    -0.06
    移
    -0.06
    رب
    -0.06
     أكثر
    -0.06
    ��
    -0.06
    ریب
    -0.06
    rimp
    -0.06
    황
    -0.06
    POSITIVE LOGITS
     Recycling
    0.07
    	do
    0.07
    .RESULT
    0.07
     owes
    0.06
     timing
    0.06
     owe
    0.06
    .Zero
    0.06
     //=
    0.06
    :function
    0.06
    []){↵
    0.06
    Activations Density 0.008%

    No Known Activations