© 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. 37883
    Prev
    Next
    INDEX
    Explanations

    settings

    np_max-act · gemini-2.0-flash

    commands and keywords related to Django database and app configurations.

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

    This neuron activates on mentions of the Django settings file (e.g. “settings.py”) or related configuration keywords.

    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
     людина
    -0.07
     آنجا
    -0.06
     گذاری
    -0.06
    ()){
↵
    -0.06
    맛
    -0.06
     viết
    -0.06
     Buddhism
    -0.06
    .Condition
    -0.06
     typingsSlinky
    -0.06
    Um
    -0.06
    POSITIVE LOGITS
    PNG
    0.07
     direct
    0.07
     stability
    0.07
     Mitt
    0.06
     bankrupt
    0.06
    /se
    0.06
     coding
    0.06
     rankings
    0.06
    -step
    0.06
     noir
    0.06
    Activations Density 0.011%

    No Known Activations