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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74676
    Prev
    Next
    INDEX
    Explanations

    Past tense

    np_max-act · gemini-2.0-flash

    This neuron detects parts of structured, numbered templates or outline formats (e.g. section labels, bullet‐point markers, and other formatting elements in a report or plan).

    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
    (_:
    -0.07
    leted
    -0.07
    Device
    -0.07
     phosph
    -0.06
     kitchens
    -0.06
    <Result
    -0.06
    DIS
    -0.06
     TableName
    -0.06
     závis
    -0.06
     Literature
    -0.06
    POSITIVE LOGITS
     แก
    0.06
     seg
    0.06
     kiếm
    0.06
     masculinity
    0.06
     GNU
    0.06
     البحر
    0.06
    kur
    0.06
    asından
    0.06
     replica
    0.06
     Actually
    0.06
    Activations Density 0.361%

    No Known Activations