© 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. 7550
    Prev
    Next
    INDEX
    Explanations

    large scale structure universe

    np_max-act · gemini-2.0-flash

    The neuron is looking for mentions of the large‐scale structure of the universe—terms like “large‐scale,” “structure,” “clustering,” and related cosmological correlation-function/perturbation theory phrases.

    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
     trapping
    -0.07
     proportion
    -0.07
     gerektir
    -0.06
    vac
    -0.06
     Worksheet
    -0.06
    heet
    -0.06
     Sheets
    -0.06
    weetalert
    -0.06
    �
    -0.06
    kd
    -0.06
    POSITIVE LOGITS
     MMI
    0.07
     našich
    0.07
     dominate
    0.06
     fence
    0.06
     reconstructed
    0.06
    тив
    0.06
    黑
    0.06
    acea
    0.06
    ІІ
    0.06
     unanswered
    0.06
    Activations Density 0.001%

    No Known Activations