© 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. 73923
    Prev
    Next
    INDEX
    Explanations

    (dir

    np_max-act · gemini-2.0-flash

    This neuron spotlights Gradle “fileTree” dependency declarations (the compile fileTree(dir:'libs', include:['*.jar']) pattern).

    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
    .getOwnPropertyDescriptor
    -0.07
    624
    -0.06
     principalColumn
    -0.06
     Scroll
    -0.06
    ，有
    -0.06
     норматив
    -0.06
     keyword
    -0.06
     ServiceProvider
    -0.06
     Bind
    -0.06
     Mana
    -0.06
    POSITIVE LOGITS
     ev
    0.06
     retreated
    0.06
    /android
    0.06
    Kevin
    0.06
     uplifting
    0.06
     unt
    0.06
     cannabin
    0.06
    346
    0.06
     appe
    0.06
    345
    0.06
    Activations Density 0.001%

    No Known Activations