© 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. 72224
    Prev
    Next
    INDEX
    Explanations

    Your

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the capitalized word “Your” (especially at the start of a sentence).

    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
     Flow
    -0.06
    itu
    -0.06
     book
    -0.06
    uctose
    -0.06
    ogo
    -0.06
     evangelical
    -0.06
    ilogy
    -0.06
    626
    -0.06
     Nonetheless
    -0.06
     permite
    -0.06
    POSITIVE LOGITS
    Your
    0.10
     Your
    0.09
    your
    0.08
     your
    0.07
     SR
    0.07
    .ur
    0.07
    .dr
    0.07
     Eur
    0.07
    .processor
    0.07
     DR
    0.07
    Activations Density 0.026%

    No Known Activations