© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59095
    Prev
    Next
    INDEX
    Explanations

    code imports

    np_max-act · gemini-2.0-flash

    imports from programming files that define utility and resource management functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on tokens that are parts of Java package or class name segments (the identifiers in import/package declarations).

    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
    竜
    -0.06
     Cr
    -0.06
     Brenda
    -0.06
     Ελλην
    -0.06
     sextreffen
    -0.06
     Woo
    -0.06
     حساب
    -0.06
     "#"
    -0.06
    &D
    -0.06
    iền
    -0.05
    POSITIVE LOGITS
     matte
    0.07
     insan
    0.07
    ۲۶
    0.06
    ас
    0.06
     explos
    0.06
    ोक
    0.06
    unctuation
    0.06
    лен
    0.06
    ाक
    0.06
     relocate
    0.06
    Activations Density 0.005%

    No Known Activations