© 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. 109190
    Prev
    Next
    INDEX
    Explanations

    img

    np_max-act · gemini-2.0-flash

    This neuron fires on code that loads a PIL Image and converts it into a NumPy array (e.g. Image.open and np.asarray calls).

    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
    ation
    -0.07
     rear
    -0.07
    ension
    -0.07
    pher
    -0.07
    arith
    -0.07
    ΑΛ
    -0.07
     стро
    -0.07
    at
    -0.07
    ber
    -0.07
     Peace
    -0.07
    POSITIVE LOGITS
    (cmd
    0.08
    	img
    0.08
     AppModule
    0.08
    cmd
    0.08
    cfg
    0.07
     cvs
    0.07
    pkg
    0.07
     img
    0.07
    tmp
    0.07
    (img
    0.07
    Activations Density 0.051%

    No Known Activations