© 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. 68511
    Prev
    Next
    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash

    The neuron fires on license‐related comment metadata—e.g. “LICENSE_AFL.txt,” “.php” license links, “license,” “obtain”—i.e. it detects license header references in source files.

    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
    Favorites
    -0.07
     princ
    -0.07
    olerance
    -0.06
    �
    -0.06
    ніп
    -0.06
    iyoruz
    -0.06
    سوب
    -0.06
    puts
    -0.06
    ЎыџNЎыџN
    -0.06
    Submit
    -0.06
    POSITIVE LOGITS
     mirror
    0.06
     coded
    0.06
    -lib
    0.06
    <T
    0.06
    影
    0.06
     персп
    0.06
     foresee
    0.06
    Skill
    0.06
     appeal
    0.06
     tossed
    0.06
    Activations Density 0.003%

    No Known Activations