© 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. 104532
    Prev
    Next
    INDEX
    Explanations

    many several

    np_max-act · gemini-2.0-flash
    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
     hovering
    -0.07
    =default
    -0.07
    ching
    -0.07
    iving
    -0.06
     failures
    -0.06
     вообще
    -0.06
     refuge
    -0.06
    。\
    -0.06
    にも
    -0.06
     آرام
    -0.06
    POSITIVE LOGITS
    fik
    0.07
     DK
    0.06
    τήσεις
    0.06
    _nullable
    0.06
    _resolve
    0.06
     Мин
    0.06
     Бел
    0.06
    '];
↵
↵
    0.06
    (sh
    0.06
    buttonShape
    0.06
    Activations Density 0.061%

    No Known Activations