© 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. 65660
    Prev
    Next
    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash

    Java code related to constructors and class instantiation.

    oai_token-act-pair · gpt-4o-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
     Duch
    -0.08
     white
    -0.06
     wandering
    -0.06
     Greg
    -0.06
    elters
    -0.06
     Track
    -0.06
     Mapper
    -0.06
     Pháp
    -0.06
     banyak
    -0.06
     jail
    -0.06
    POSITIVE LOGITS
    (/[
    0.08
    .lineTo
    0.07
     інозем
    0.07
     خام
    0.06
     hayvan
    0.06
     система
    0.06
    -Cs
    0.06
    ocial
    0.06
    \_
    0.06
    (car
    0.06
    Activations Density 0.013%

    No Known Activations