© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41152
    Prev
    Next
    INDEX
    Explanations

    System namespace

    np_max-act · gemini-2.0-flash

    The neuron specializes in picking out code namespace or library identifiers (the capitalized module names that follow “namespace” or appear in dotted API paths).

    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
    оген
    -0.07
     Scalia
    -0.06
    زب
    -0.06
     dẫn
    -0.06
     Prosper
    -0.06
    ident
    -0.06
    Command
    -0.06
    PickerController
    -0.06
    DataStream
    -0.06
     World
    -0.06
    POSITIVE LOGITS
    )?.
    0.06
    ()?.
    0.06
    ового
    0.06
     наш
    0.06
     üçüncü
    0.06
     však
    0.06
     Прав
    0.06
     titten
    0.06
     erfolgre
    0.06
    ократи
    0.05
    Activations Density 0.007%

    No Known Activations