Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55073
    Prev
    Next
    INDEX
    Explanations

    Names "Henri" or "Andre"

    np_max-act · gemini-2.0-flash

    This neuron fires whenever it sees the given name "Andre."

    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
    31
    -0.07
    /pre
    -0.07
    xies
    -0.06
    /high
    -0.06
     Res
    -0.06
    -summary
    -0.06
    40
    -0.06
    3
    -0.06
     sqrt
    -0.06
    key
    -0.06
    POSITIVE LOGITS
     Jean
    0.09
    Jean
    0.09
     François
    0.08
    Nic
    0.08
     Nicolas
    0.08
     Francois
    0.07
     Johann
    0.07
     Andre
    0.07
     Maurice
    0.07
    ylv
    0.07
    Activations Density 0.103%

    No Known Activations