Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 86129
    Prev
    Next
    INDEX
    Explanations

    Email subscriptions and newsletters

    np_max-act · gemini-2.0-flash

    The neuron detects the boilerplate consent language around submitting or entering your email address (e.g. “By submitting your details …”).

    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
     ashamed
    -0.06
    /<
    -0.06
    �
    -0.06
    штов
    -0.06
    нош
    -0.06
     forcing
    -0.06
     раздел
    -0.06
    (pdev
    -0.06
    .emp
    -0.06
    看着
    -0.05
    POSITIVE LOGITS
     Fish
    0.06
     License
    0.06
     Plant
    0.06
    	reg
    0.06
     transactions
    0.06
     apple
    0.06
    Click
    0.06
     unlink
    0.06
     irrigation
    0.06
     naive
    0.06
    Activations Density 0.005%

    No Known Activations