© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    layout

    np_max-act · gemini-2.0-flash

    This neuron fires on Android XML layout attributes specifying numeric sizing or weighting (e.g. layout_width, layout_height, and layout_weight values).

    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
    CppCodeGenWriteBarrier
    -0.07
    	elif
    -0.06
     psycopg
    -0.06
    smouth
    -0.06
    @GeneratedValue
    -0.06
    (xi
    -0.06
    .firebase
    -0.06
     OID
    -0.06
    ortion
    -0.06
    blk
    -0.06
    POSITIVE LOGITS
     WAY
    0.07
    .TXT
    0.06
     reading
    0.06
     gió
    0.06
     /*!<
    0.06
     раст
    0.06
     Clara
    0.06
     haha
    0.06
    iful
    0.06
     ARRAY
    0.06
    Activations Density 0.002%

    No Known Activations