© 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. 3-RESID-POST-AA
    11. 93857
    Prev
    Next
    INDEX
    Explanations

    dies

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .arg
    -0.07
    後の
    -0.07
     SUN
    -0.06
    ate
    -0.06
     집
    -0.06
    .Nav
    -0.06
    .ast
    -0.06
     Cot
    -0.06
    length
    -0.06
     Highlander
    -0.06
    POSITIVE LOGITS
     dies
    0.24
     Dies
    0.16
    Dies
    0.13
    .iloc
    0.07
    ies
    0.07
    userService
    0.07
    チ
    0.06
    される
    0.06
    ília
    0.06
    [level
    0.06
    Activations Density 0.003%

    No Known Activations