© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73758
    Prev
    Next
    INDEX
    Explanations

    Tabs and pages

    np_max-act · gemini-2.0-flash

    The neuron fires on identifiers naming UI container or page‐style widget classes (e.g. “PageControl,” “TabSheet,” “TabFolder,” “TabItem,” etc.).

    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
    _bel
    -0.07
    emp
    -0.06
    多少
    -0.06
    gap
    -0.06
     Trials
    -0.06
    dk
    -0.06
    481
    -0.06
    uc
    -0.06
     debates
    -0.06
     Arc
    -0.06
    POSITIVE LOGITS
    youtube
    0.07
    をする
    0.07
     фот
    0.07
     느
    0.07
    ViewItem
    0.06
    .EventHandler
    0.06
    姿
    0.06
    etical
    0.06
     onsite
    0.06
     STACK
    0.06
    Activations Density 0.030%

    No Known Activations