© 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. 19-RESID-POST-AA
    11. 91205
    Prev
    Next
    INDEX
    Explanations

    ridic

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     primeiro
    -0.07
     afterward
    -0.06
    т
    -0.06
    -to
    -0.06
    :new
    -0.06
    ุมภาพ
    -0.06
     visas
    -0.06
    だが
    -0.06
     coming
    -0.06
    enter
    -0.06
    POSITIVE LOGITS
     çek
    0.08
     sadd
    0.08
    ={"/
    0.07
     Mid
    0.07
     Osc
    0.07
     IPC
    0.07
     actualizar
    0.07
    詞
    0.07
     Ск
    0.07
    rif
    0.07
    Activations Density 0.001%

    No Known Activations