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. 85525
    Prev
    Next
    INDEX
    Explanations

    Flutter

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “flutter,” detecting mentions of the Flutter framework regardless of context.

    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
     sight
    -0.07
     azi
    -0.07
    óz
    -0.07
     Kop
    -0.07
    CppI
    -0.07
    ordinate
    -0.07
     kil
    -0.06
     zi
    -0.06
    에도
    -0.06
     yö
    -0.06
    POSITIVE LOGITS
     flutter
    0.10
     Flutter
    0.07
    .GREEN
    0.07
    PressEvent
    0.07
    jspb
    0.07
    メント
    0.06
    /flutter
    0.06
    @FindBy
    0.06
    ุณภาพ
    0.06
    หล
    0.06
    Activations Density 0.001%

    No Known Activations