© 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. 57072
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on the indefinite article “a” when it appears in file‐reading commands (e.g. “read a CSV/JSON file”).

    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
    TOT
    -0.07
    565
    -0.07
    olume
    -0.07
    Builders
    -0.07
     Investor
    -0.07
     Arcade
    -0.07
     Bid
    -0.07
     bedroom
    -0.06
    embrance
    -0.06
    　 　 　 　 　 　
    -0.06
    POSITIVE LOGITS
    anken
    0.07
     sayı
    0.07
     Và
    0.06
     uprav
    0.06
     aime
    0.06
    оград
    0.06
     Canterbury
    0.06
     maybe
    0.06
     leftover
    0.06
     pis
    0.06
    Activations Density 0.052%

    No Known Activations