© 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. 128426
    Prev
    Next
    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash

    This neuron activates on verbs and phrases marking the start of a play or inning in baseball play-by-play (e.g. “led off,” “started,” “off”).

    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
    итив
    -0.07
     Most
    -0.07
     Holding
    -0.06
     atleast
    -0.06
    д
    -0.06
    >*/↵
    -0.06
     الرسمي
    -0.06
    ↵
    -0.06
     exact
    -0.06
     mẹ
    -0.06
    POSITIVE LOGITS
     dateFormatter
    0.07
     WW
    0.06
     Beh
    0.06
    污
    0.06
     وا
    0.06
    intel
    0.06
    ilor
    0.06
    cstdio
    0.06
     illum
    0.06
     UD
    0.06
    Activations Density 0.005%

    No Known Activations