© 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. 9441
    Prev
    Next
    INDEX
    Explanations

    video controls

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML5 video tag attribute tokens (e.g. controls, autoplay, autobuffer, preload, loop, muted, etc.).

    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
    trieve
    -0.06
     대부분
    -0.06
    他們
    -0.06
     매매가
    -0.06
     orbital
    -0.06
     Davis
    -0.06
    rnd
    -0.06
    DEFINED
    -0.06
     trapping
    -0.06
    ('\\
    -0.06
    POSITIVE LOGITS
    Zh
    0.07
     ascii
    0.07
    ='<
    0.07
     commuter
    0.07
     Exposure
    0.06
     artık
    0.06
     كان
    0.06
     crashed
    0.06
     zam
    0.06
    eşil
    0.06
    Activations Density 0.036%

    No Known Activations