© 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
    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. 126950
    Prev
    Next
    INDEX
    Explanations

    married

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of marital status, especially the word “married” (and its Russian equivalents “женат”/“жена”).

    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
    ihad
    -0.07
    orte
    -0.07
     womens
    -0.07
     Hed
    -0.06
    	select
    -0.06
     SEX
    -0.06
     passages
    -0.06
     melody
    -0.06
     cdr
    -0.06
     COD
    -0.06
    POSITIVE LOGITS
    ;top
    0.07
     vyšší
    0.07
    (connectionString
    0.07
     گردش
    0.07
     علاوه
    0.06
    _ef
    0.06
    ,&
    0.06
    =nil
    0.06
    _vs
    0.06
    ्रमण
    0.06
    Activations Density 0.022%

    No Known Activations