Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84812
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting C++ console‐output lines—i.e. `std::cout << …` statements with string literals (the `<<` operators and quoted text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions surrounding constructors in C++.

    oai_token-act-pair · gpt-4o-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
     Coral
    -0.09
    _Clear
    -0.07
     characterize
    -0.06
     teacher
    -0.06
     JPanel
    -0.06
     precious
    -0.06
     tabPage
    -0.06
    .Duration
    -0.06
    سوب
    -0.06
    Scoped
    -0.06
    POSITIVE LOGITS
    �
    0.08
     đi
    0.07
     ho
    0.06
     commissioned
    0.06
    .sc
    0.06
    &o
    0.06
    .Im
    0.06
    |wx
    0.06
     denně
    0.06
     advant
    0.06
    Activations Density 0.023%

    No Known Activations