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. 84437
    Prev
    Next
    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting the standard UIApplication-lifecycle comment lines (the “Sent when the application is about to…,” “Use this method to…,” etc.) that appear in AppDelegate method bodies.

    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
    Variable
    -0.08
     Giants
    -0.06
    Exc
    -0.06
    Day
    -0.06
     '\''
    -0.06
    	point
    -0.06
    Translation
    -0.06
    Pixel
    -0.06
    がない
    -0.06
    Ocean
    -0.06
    POSITIVE LOGITS
     bbw
    0.07
    :]↵↵
    0.06
     jobId
    0.06
    нила
    0.06
    -interface
    0.06
     текст
    0.06
    .§
    0.06
    _delta
    0.06
    _context
    0.06
    _CREATE
    0.06
    Activations Density 0.015%

    No Known Activations