© 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 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. 38475
    Prev
    Next
    INDEX
    Explanations

    calculator

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on occurrences of the word “calculator.”

    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
     sorted
    -0.08
    Entries
    -0.07
    Day
    -0.07
    187
    -0.07
     anterior
    -0.07
    67
    -0.07
     EVENT
    -0.06
     Dead
    -0.06
    ITED
    -0.06
     stormed
    -0.06
    POSITIVE LOGITS
     calculator
    0.09
     каль
    0.07
     Calculator
    0.07
    ισμ
    0.07
    culator
    0.07
    calculator
    0.07
    (jQuery
    0.06
     Toolkit
    0.06
    "./
    0.06
     frivol
    0.06
    Activations Density 0.004%

    No Known Activations