© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58554
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects parenthesized stock‐exchange ticker mentions (e.g. “(NYSE: XYZ)” or “(NASDAQ: ABC)”).

    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
    Total
    -0.07
     kterého
    -0.07
    434
    -0.07
     btnCancel
    -0.07
     stř
    -0.07
     exact
    -0.07
    的地
    -0.06
     sep
    -0.06
     Rating
    -0.06
     Ultimate
    -0.06
    POSITIVE LOGITS
     Фед
    0.06
    lias
    0.06
     lowers
    0.06
     kop
    0.06
    (currency
    0.06
    \t
    0.06
     Shir
    0.06
     juicy
    0.05
    iram
    0.05
    ullan
    0.05
    Activations Density 0.003%

    No Known Activations