© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57650
    Prev
    Next
    INDEX
    Explanations

    _BEGIN

    np_max-act · gemini-2.0-flash

    This neuron activates on the Objective-C nullability annotation markers (the NS_ASSUME_NONNULL _BEGIN/END macros).

    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
     listop
    -0.06
    GROUP
    -0.06
    flash
    -0.06
    Video
    -0.06
     initialised
    -0.06
     framed
    -0.06
    _PRESS
    -0.06
     opat
    -0.06
    etrain
    -0.06
     Mitch
    -0.06
    POSITIVE LOGITS
    _BEGIN
    0.08
    оні
    0.07
     grabbing
    0.06
     recommends
    0.06
     sacrifice
    0.06
     Carnegie
    0.06
     】
    0.06
    midt
    0.06
    jí
    0.06
    aea
    0.06
    Activations Density 0.001%

    No Known Activations