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

    Neuronpedia

    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. 13815
    Prev
    Next
    INDEX
    Explanations

    crop production

    np_max-act · gemini-2.0-flash

    The neuron is principally triggered by numeric data—quantities, percentages, dates, measurements, and statistical figures—in the text.

    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
    렸
    -0.07
    Stra
    -0.06
    �
    -0.06
     Роб
    -0.06
     rowspan
    -0.06
    didn
    -0.06
     messed
    -0.06
     heavens
    -0.06
     showcased
    -0.06
    -li
    -0.06
    POSITIVE LOGITS
     kort
    0.06
    nilai
    0.06
    agraph
    0.06
     Beer
    0.06
     الاست
    0.06
    Warn
    0.06
    PLETED
    0.06
    abolic
    0.06
     �
    0.06
     ez
    0.06
    Activations Density 0.007%

    No Known Activations