© 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. 127030
    Prev
    Next
    INDEX
    Explanations

    programming and/or code

    np_max-act · gemini-2.0-flash

    The neuron flags spots where code is talking about or manipulating optional function parameters (e.g. default args, *args/**kwargs, option_key/value).

    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
     trenches
    -0.08
     aprender
    -0.07
     Adv
    -0.07
     Brooklyn
    -0.07
     verbess
    -0.06
     Attacks
    -0.06
     نویس
    -0.06
     reh
    -0.06
     sharedPreferences
    -0.06
     dudes
    -0.06
    POSITIVE LOGITS
    افر
    0.06
     forty
    0.06
    ็จพระ
    0.06
    عاد
    0.06
     mutually
    0.06
    contact
    0.06
    click
    0.06
    Cancelled
    0.06
    toi
    0.06
    Wunused
    0.06
    Activations Density 0.197%

    No Known Activations