© 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. 110478
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on runtime‐error messages about invalid property or array access (e.g. “Trying to access…,” “Cannot read properties of null,” etc.).

    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
    ildren
    -0.06
     precedent
    -0.06
     desn
    -0.06
     spreadsheet
    -0.06
    존
    -0.06
     Chang
    -0.06
    .policy
    -0.06
    cdc
    -0.06
     forEach
    -0.06
     Tomb
    -0.06
    POSITIVE LOGITS
     Δια
    0.07
    $string
    0.06
    .localtime
    0.06
    (signature
    0.06
    UserRole
    0.06
    Attribute
    0.06
    ΙΑ
    0.06
    าหาร
    0.06
    ่านมา
    0.06
    ďte
    0.06
    Activations Density 0.017%

    No Known Activations