© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128250
    Prev
    Next
    INDEX
    Explanations

    Code, questions, and advice

    np_max-act · gemini-2.0-flash

    issues related to user interface event handling in programming contexts.

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

    The neuron detects modals and suggestion-oriented words (e.g. can, should, maybe, try, use) that signal advice or recommendation contexts.

    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
    instruction
    -0.06
     askeri
    -0.06
    SQL
    -0.06
    教育
    -0.06
    .Callback
    -0.06
     tapi
    -0.06
    输
    -0.06
     =↵↵
    -0.06
    ConnectionFactory
    -0.06
    onChange
    -0.06
    POSITIVE LOGITS
     второй
    0.07
    /footer
    0.06
    -orders
    0.06
     büyük
    0.06
    /testify
    0.06
    aders
    0.06
    .getPlayer
    0.06
    τέλε
    0.06
    buquerque
    0.06
     الحديث
    0.06
    Activations Density 0.249%

    No Known Activations