© 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. 11-RESID-POST-AA
    11. 51283
    Prev
    Next
    INDEX
    Explanations

    complaining and drama

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prescribe
    -0.07
     beach
    -0.07
    _cc
    -0.06
    Wednesday
    -0.06
     Benefits
    -0.06
    Clark
    -0.06
    िष
    -0.06
     Saturday
    -0.06
     ambition
    -0.06
     vir
    -0.05
    POSITIVE LOGITS
    istream
    0.07
    一个
    0.07
    izmet
    0.07
     όμως
    0.06
    �
    0.06
    IDDEN
    0.06
     nat
    0.06
     JSX
    0.06
     P
    0.06
    .train
    0.06
    Activations Density 0.053%

    No Known Activations