© 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. 91235
    Prev
    Next
    INDEX
    Explanations

    fairy tales

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences (even split across tokens) of the name “Cenerentola” (the Italian form of Cinderella).

    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
    -heading
    -0.06
    .AutoField
    -0.06
    曜
    -0.06
    MouseMove
    -0.06
    자의
    -0.06
    ’te
    -0.06
     WooCommerce
    -0.06
     amigo
    -0.06
     прой
    -0.06
    fout
    -0.06
    POSITIVE LOGITS
    Hola
    0.07
    -report
    0.07
     tale
    0.07
     elektron
    0.07
     battles
    0.06
     Encore
    0.06
     toen
    0.06
    Consum
    0.06
     Tale
    0.06
     technik
    0.06
    Activations Density 0.009%

    No Known Activations