© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109487
    Prev
    Next
    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on CSS style declarations—that is, property names and their values within `<style>` blocks or CSS files.

    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
    _WORK
    -0.07
    cost
    -0.06
     recherche
    -0.06
    İng
    -0.06
     numpy
    -0.06
     δια
    -0.06
    confirmation
    -0.06
    (side
    -0.06
    claimer
    -0.06
    _tensors
    -0.06
    POSITIVE LOGITS
    ैं।↵
    0.07
    L
    0.06
     hasil
    0.06
     Başkan
    0.06
     Viewer
    0.06
     scrape
    0.06
    lou
    0.06
    _inches
    0.06
    ็บไซต
    0.06
     Colleg
    0.06
    Activations Density 0.005%

    No Known Activations