Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129458
    Prev
    Next
    INDEX
    Explanations

    CSS properties

    np_max-act · gemini-2.0-flash

    This neuron detects numeric CSS values (e.g. “20px”, “1.5em”) and related style-property/value contexts in CSS rules.

    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
     Framework
    -0.06
    δρο
    -0.06
    connections
    -0.06
    �
    -0.06
    знача
    -0.06
     manipulated
    -0.05
     strategic
    -0.05
     कहत
    -0.05
     lips
    -0.05
    rand
    -0.05
    POSITIVE LOGITS
     hvordan
    0.07
    оюз
    0.07
     Amar
    0.07
     AVCapture
    0.07
    .LayoutParams
    0.07
    _ylabel
    0.07
     اروپا
    0.06
     RTAL
    0.06
     excer
    0.06
    .Players
    0.06
    Activations Density 0.028%

    No Known Activations