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

    Neuronpedia

    Jacobian LensNEW
    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. 27-RESID-POST-AA
    11. 11178
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <Employee
    -0.06
     [...]
    -0.06
     зуст
    -0.06
    ódigo
    -0.06
    .attachment
    -0.06
    (element
    -0.06
    筆
    -0.06
    考
    -0.06
     سپس
    -0.06
     câ
    -0.06
    POSITIVE LOGITS
    ymax
    0.07
     tarn
    0.07
     Hok
    0.07
    倉
    0.06
    дам
    0.06
     개발
    0.06
     Amerika
    0.06
    ハイ
    0.06
    ardır
    0.06
    латы
    0.06
    Activations Density 0.006%

    No Known Activations