© 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. 53996
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron fires on sentences describing a baseball player’s professional career, especially mentions of playing in Major League Baseball for specific teams.

    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
     ftp
    -0.07
    fab
    -0.06
    Dump
    -0.06
    еле
    -0.06
    üns
    -0.06
    _patches
    -0.06
    _PICTURE
    -0.06
     poil
    -0.06
     Pack
    -0.06
     hill
    -0.06
    POSITIVE LOGITS
    бря
    0.07
           
    0.06
     disparate
    0.06
     신입
    0.06
    士
    0.06
     continuar
    0.06
     мови
    0.06
     subtly
    0.06
     соблюд
    0.06
    .translatesAutoresizingMaskIntoConstraints
    0.06
    Activations Density 0.018%

    No Known Activations