© 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. 109335
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron detects VBA statements that toggle Excel’s application‐level settings (e.g. Application.ScreenUpdating, calculation mode, status bar updates).

    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
    عمل
    -0.07
    .templates
    -0.07
    ่างก
    -0.07
     select
    -0.07
    �
    -0.06
     PROCUREMENT
    -0.06
     QPainter
    -0.06
    ारण
    -0.06
    sprintf
    -0.06
    高度
    -0.06
    POSITIVE LOGITS
     Deadline
    0.06
     communicating
    0.06
     ücretsiz
    0.06
    Future
    0.06
     idle
    0.06
     gdy
    0.06
    -gap
    0.06
     والتي
    0.05
    Prince
    0.05
     elimin
    0.05
    Activations Density 0.006%

    No Known Activations