© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7892
    Prev
    Next
    INDEX
    Explanations

    _types

    np_max-act · gemini-2.0-flash

    The neuron activates on PHP type‐declaration and return‐type syntax (e.g. “declare(strict_types=1)” and “function setUp(): void”).

    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
     GEN
    -0.07
     Broadway
    -0.06
     позд
    -0.06
    .setBounds
    -0.06
    obbies
    -0.06
     làm
    -0.06
    PositiveButton
    -0.06
    ound
    -0.06
     비밀글
    -0.06
    _tabs
    -0.06
    POSITIVE LOGITS
     catastrophe
    0.06
    mesi
    0.06
    -border
    0.06
     asla
    0.06
     =>
    0.06
    -checked
    0.06
     decades
    0.06
     settled
    0.06
     ün
    0.06
     divorced
    0.06
    Activations Density 0.038%

    No Known Activations