© 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. 44243
    Prev
    Next
    INDEX
    Explanations

    \Facades

    np_max-act · gemini-2.0-flash

    The neuron activates on PHP “use”/import lines that reference Laravel’s Illuminate namespaces (e.g. Illuminate\Support\Facades, Illuminate\Database\Schema\Blueprint, Illuminate\Database\Migrations\Migration).

    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
     arrows
    -0.08
     installer
    -0.06
     scrolls
    -0.06
    เต
    -0.06
    erk
    -0.06
    urrect
    -0.06
    ující
    -0.06
    ์แ
    -0.06
    골
    -0.06
    л
    -0.06
    POSITIVE LOGITS
    -catching
    0.07
    .constraints
    0.06
    。。
    0.06
     '-',
    0.06
     vài
    0.06
     cellphone
    0.06
    centaje
    0.06
    scheduled
    0.06
    __(*
    0.06
    \Facades
    0.06
    Activations Density 0.001%

    No Known Activations