© 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. 30969
    Prev
    Next
    INDEX
    Explanations

    zoning and residences

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of zoning classifications or land‐use categories (e.g. “Residential-9600,” “Highway Commercial,” “Industrial,” “single‐family residences,” 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
    .;.;
    -0.07
    hole
    -0.06
     Lola
    -0.06
    utowired
    -0.06
    研究
    -0.06
     Wir
    -0.06
     explored
    -0.06
    _chain
    -0.06
     CLIIIK
    -0.06
     глиб
    -0.05
    POSITIVE LOGITS
     第三
    0.07
    	priv
    0.07
    िष
    0.07
    pan
    0.06
    _column
    0.06
    体
    0.06
    Dist
    0.06
     benefici
    0.06
    Their
    0.06
    (ml
    0.06
    Activations Density 0.014%

    No Known Activations