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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 536
    Prev
    Next
    INDEX
    Explanations

    .dart

    np_max-act · gemini-2.0-flash

    The neuron fires on Dart code import lines and “.dart” file‐extension references—that is, spots where Flutter/Dart source files are being imported or named.

    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
     उ
    -0.07
    ,module
    -0.06
     vowels
    -0.06
    (redis
    -0.06
     Ir
    -0.06
     IPPROTO
    -0.06
    oggler
    -0.06
     몸을
    -0.06
     serv
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .dart
    0.10
    -leading
    0.07
    months
    0.06
    ISCO
    0.06
    _rem
    0.06
    rang
    0.06
    Getting
    0.06
    295
    0.06
    .childNodes
    0.06
    :T
    0.06
    Activations Density 0.000%

    No Known Activations