© 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. 93713
    Prev
    Next
    INDEX
    Explanations

    can (foreign languages)

    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
    каж
    -0.07
     Việc
    -0.06
    Việc
    -0.06
     guts
    -0.06
    _CSS
    -0.06
    partment
    -0.06
     Title
    -0.05
     stalo
    -0.05
    -T
    -0.05
     Hunger
    -0.05
    POSITIVE LOGITS
    ','-
    0.08
    藏
    0.07
     podem
    0.07
    (reordered
    0.07
     mož
    0.07
    �
    0.06
     Pediatrics
    0.06
    ynec
    0.06
     ORM
    0.06
    ů
    0.06
    Activations Density 0.023%

    No Known Activations