© 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. 62295
    Prev
    Next
    INDEX
    Explanations

    Code and technical descriptions

    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
     напис
    -0.07
    .perform
    -0.07
    さんの
    -0.07
     Provincial
    -0.07
    "strings
    -0.07
     revis
    -0.06
    ;"↵
    -0.06
     Wolves
    -0.06
    titles
    -0.06
    /twitter
    -0.06
    POSITIVE LOGITS
     Janeiro
    0.07
    (sid
    0.07
    Device
    0.06
     레이
    0.06
    ϊ
    0.06
    884
    0.06
    ксп
    0.06
     candle
    0.06
    EMA
    0.06
     choix
    0.06
    Activations Density 0.000%

    No Known Activations