© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128548
    Prev
    Next
    INDEX
    Explanations

    bgcolor

    np_max-act · gemini-2.0-flash

    This neuron detects color‐specification values (e.g. numeric or hex codes) in HTML/CSS, such as the bgcolor attribute’s color values.

    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
    Tweet
    -0.07
    .CenterScreen
    -0.06
     sớm
    -0.06
     breat
    -0.06
    Sunday
    -0.06
     сум
    -0.06
     padd
    -0.06
     clearTimeout
    -0.06
    토토
    -0.06
    редит
    -0.06
    POSITIVE LOGITS
    аров
    0.08
     bgcolor
    0.08
    قد
    0.06
    ğü
    0.06
    enco
    0.06
    pering
    0.06
     pdu
    0.06
     bgColor
    0.06
    백
    0.06
    ayo
    0.06
    Activations Density 0.000%

    No Known Activations