© 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. 69620
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     MLA
    -0.06
    terminate
    -0.06
     xong
    -0.06
     mashed
    -0.06
     ح
    -0.06
     pare
    -0.06
     bán
    -0.06
    лат
    -0.06
    Kids
    -0.06
    David
    -0.06
    POSITIVE LOGITS
    hodob
    0.07
     classify
    0.07
    enzhen
    0.06
    ugo
    0.06
     canyon
    0.06
     карт
    0.06
    �
    0.06
     قالب
    0.06
     showroom
    0.05
    saldo
    0.05
    Activations Density 0.077%

    No Known Activations