© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 92037
    Prev
    Next
    INDEX
    Explanations

    The

    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
     Mobility
    -0.07
     Byl
    -0.07
     versatility
    -0.07
     Trong
    -0.06
     Area
    -0.06
     ACLU
    -0.06
     Shade
    -0.06
     Belfast
    -0.06
     pár
    -0.06
     Kỳ
    -0.06
    POSITIVE LOGITS
    .Resource
    0.07
    :${
    0.07
    -BEGIN
    0.07
    ressing
    0.06
    .Connection
    0.06
    sumer
    0.06
     ніч
    0.06
    (sizeof
    0.06
    روض
    0.06
    (月
    0.06
    Activations Density 0.028%

    No Known Activations