© 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. 29754
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash

    The neuron detects words that call out required conventions or specifications—terms like “conventions,” “needs,” “properties,” and “required.”

    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
    Je
    -0.06
    between
    -0.06
     Woo
    -0.06
     {[
    -0.06
     deserted
    -0.06
    mět
    -0.06
    timezone
    -0.06
    imum
    -0.06
    (dynamic
    -0.06
     abuse
    -0.06
    POSITIVE LOGITS
    Migration
    0.07
     SCH
    0.07
    .NO
    0.07
     Liter
    0.06
    .th
    0.06
     taille
    0.06
    襲
    0.06
    �
    0.06
     λίγ
    0.06
    ๐
    0.06
    Activations Density 0.104%

    No Known Activations