© 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. 13624
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    color definitions and styling information in code.

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

    The neuron is picking up CSS style tokens related to color properties (e.g., “color”, “_bg”, “_fg”, “:”, hex color codes).

    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
    atism
    -0.07
     είχαν
    -0.06
    .Bot
    -0.06
    OpenHelper
    -0.06
    Robot
    -0.06
     shadows
    -0.06
    θήκη
    -0.06
    										 
    -0.06
    _Not
    -0.06
    _FIRE
    -0.06
    POSITIVE LOGITS
     daunting
    0.07
    ."
    0.06
          ↵
    0.06
     like
    0.06
     повідом
    0.06
     affili
    0.05
     recovered
    0.05
     depress
    0.05
     sensed
    0.05
     fø
    0.05
    Activations Density 0.013%

    No Known Activations