© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 795
    Prev
    Next
    INDEX
    Explanations

    CSS styling

    np_max-act · gemini-2.0-flash

    The neuron fires on CSS numeric values with decimal fractions (e.g. “1.2998046875px”), i.e. it detects floating-point numbers in style rules.

    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
    ंगल
    -0.07
     anybody
    -0.06
    Know
    -0.06
    otions
    -0.06
     died
    -0.06
     Know
    -0.06
    /Users
    -0.06
    様
    -0.06
    /software
    -0.06
    127
    -0.06
    POSITIVE LOGITS
     Slip
    0.06
    (prod
    0.06
     Он
    0.06
     Laur
    0.06
     alerted
    0.06
    ffa
    0.06
    WebElement
    0.06
     nudity
    0.06
     profiling
    0.06
     नद
    0.06
    Activations Density 0.008%

    No Known Activations