© 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. 15-RESID-POST-AA
    11. 64318
    Prev
    Next
    INDEX
    Explanations

    to

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hol
    -0.06
    -master
    -0.06
     genome
    -0.06
     jel
    -0.06
     deflect
    -0.06
     purification
    -0.06
    LEG
    -0.06
    -dess
    -0.06
    vasive
    -0.06
     em
    -0.06
    POSITIVE LOGITS
    eatures
    0.06
    .REQUEST
    0.06
     ре
    0.06
    Par
    0.06
    549
    0.06
    icot
    0.06
    Sau
    0.06
    天堂
    0.06
    (fieldName
    0.06
     satin
    0.06
    Activations Density 0.000%

    No Known Activations