© 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. 126956
    Prev
    Next
    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash

    code snippets and elements related to user interface interactions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the word “focus,” in particular when it appears as part of event-handler names or attributes (e.g. onFocus, .focus(), focus event bindings).

    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
    74
    -0.07
    olt
    -0.06
    .reload
    -0.06
    ipient
    -0.06
    elps
    -0.06
    elaide
    -0.06
    یر
    -0.06
    orizontal
    -0.06
    ullet
    -0.06
    Enh
    -0.06
    POSITIVE LOGITS
     ukaz
    0.08
    :focus
    0.07
    */
↵
    0.07
     Müz
    0.07
     equipos
    0.06
     gust
    0.06
    .blur
    0.06
     fas
    0.06
    �
    0.06
     gold
    0.06
    Activations Density 0.002%

    No Known Activations