© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13636
    Prev
    Next
    INDEX
    Explanations

    Armstrong and Woods

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the name “Armstrong,” especially in references to Lance Armstrong.

    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
    �
    -0.06
    764
    -0.06
    590
    -0.06
    embrance
    -0.06
    pleado
    -0.06
    :'/
    -0.06
    639
    -0.06
    NotFound
    -0.06
    (Tag
    -0.06
     Board
    -0.06
    POSITIVE LOGITS
     chiếc
    0.07
     modo
    0.07
     bitterness
    0.06
    GREEN
    0.06
    _shop
    0.06
    feeds
    0.06
     serviced
    0.06
     Mish
    0.06
     gard
    0.06
    虚
    0.06
    Activations Density 0.004%

    No Known Activations