© 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. 38409
    Prev
    Next
    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of creating or converting data into NumPy arrays (i.e. uses of “numpy.array”).

    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
    _named
    -0.06
     frontier
    -0.06
     กำ
    -0.06
     dereg
    -0.06
     Зав
    -0.06
     increment
    -0.06
    _Details
    -0.05
     conserve
    -0.05
    try
    -0.05
    manent
    -0.05
    POSITIVE LOGITS
    伊
    0.07
    >Note
    0.07
    Registro
    0.06
     skills
    0.06
     Northwestern
    0.06
     UITextView
    0.06
    .inflate
    0.06
    ��
    0.06
     callable
    0.06
    _MPI
    0.06
    Activations Density 0.027%

    No Known Activations