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. 130316
    Prev
    Next
    INDEX
    Explanations

    Touch

    np_max-act · gemini-2.0-flash

    This neuron detects XML header tokens specific to Apple’s Interface Builder (e.g. the “com.apple.InterfaceBuilder…CocoaTouch.IB” storyboard/nib metadata).

    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
    :@
    -0.08
    >"+
    -0.07
    (import
    -0.07
     notification
    -0.06
     "%.
    -0.06
    Defaults
    -0.06
     CHP
    -0.06
    /:
    -0.06
     вс
    -0.06
    ähr
    -0.06
    POSITIVE LOGITS
     Potato
    0.07
     quil
    0.06
    violent
    0.06
     rodin
    0.06
    boro
    0.06
    การท
    0.06
    _comb
    0.06
    ategic
    0.06
     yerde
    0.06
    ковий
    0.06
    Activations Density 0.006%

    No Known Activations