© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54061
    Prev
    Next
    INDEX
    Explanations

    centres

    np_max-act · gemini-2.0-flash

    This neuron detects past-participial (–ed) verb forms typically used in passive constructions.

    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
     Saturdays
    -0.06
    _company
    -0.06
     Your
    -0.06
     duct
    -0.06
    _confirm
    -0.06
    ाउ
    -0.06
    ushi
    -0.06
    Your
    -0.06
     Allow
    -0.06
    .workspace
    -0.05
    POSITIVE LOGITS
     dov
    0.07
    .getFloat
    0.06
     конс
    0.06
     tus
    0.06
     карт
    0.06
     QPixmap
    0.06
    [contains
    0.06
    .xml
    0.06
    $tpl
    0.06
    داد
    0.06
    Activations Density 0.172%

    No Known Activations