© 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. 7-RESID-POST-AA
    6. 56330
    Prev
    Next
    INDEX
    Explanations

    religions

    np_max-act · gemini-2.0-flash

    mentions of religion or religious affiliation (references to faith, beliefs, or religious groups).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     timeless
    -0.07
    lah
    -0.07
     Germany
    -0.07
    _consumer
    -0.07
     PB
    -0.06
    тап
    -0.06
    Decorator
    -0.06
    ($)
    -0.06
    /setup
    -0.06
     Cast
    -0.06
    POSITIVE LOGITS
    。それ
    0.06
     Safari
    0.06
     Farmer
    0.06
    .accuracy
    0.06
    .addCell
    0.06
    Coins
    0.06
    enção
    0.06
    mse
    0.06
    sic
    0.06
     claim
    0.06
    Activations Density 0.165%

    No Known Activations