© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 105065
    Prev
    Next
    INDEX
    Explanations

    Dorothy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trấn
    -0.07
     мед
    -0.07
     Ping
    -0.06
     medidas
    -0.06
    เขต
    -0.06
    .Meta
    -0.06
    /msg
    -0.06
    mit
    -0.06
     absol
    -0.06
    _ma
    -0.06
    POSITIVE LOGITS
    venting
    0.08
     Rochester
    0.07
     costo
    0.07
    .Root
    0.06
     DOS
    0.06
    ,col
    0.06
     Stalin
    0.06
    ام
    0.06
     Powell
    0.06
     Dorothy
    0.06
    Activations Density 0.001%

    No Known Activations