© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89111
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    CSS properties and their related issues in web development contexts.

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

    The neuron is detecting the start of a CSS rule block—i.e. the “{” that opens a CSS declaration set.

    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
     consul
    -0.06
    やる
    -0.06
    _<?
    -0.06
    üş
    -0.06
    Expl
    -0.06
    pon
    -0.06
    Its
    -0.06
    UpInside
    -0.06
     Antarctica
    -0.06
    แดง
    -0.06
    POSITIVE LOGITS
    osaic
    0.07
     intimate
    0.07
     ${(
    0.07
     Craft
    0.07
     Admin
    0.07
     criteria
    0.07
    =input
    0.07
     whiskey
    0.06
    cular
    0.06
     raster
    0.06
    Activations Density 0.010%

    No Known Activations