© 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. 103925
    Prev
    Next
    INDEX
    Explanations

    Left

    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
     rinse
    -0.07
     Roulette
    -0.07
     Ric
    -0.07
     Ros
    -0.07
    Ral
    -0.07
     Book
    -0.07
     ResourceBundle
    -0.07
    рою
    -0.07
    JSONArray
    -0.07
     dan
    -0.07
    POSITIVE LOGITS
     left
    0.15
     Left
    0.13
     LEFT
    0.13
    Left
    0.12
    左
    0.10
    -left
    0.10
    _Left
    0.09
    .left
    0.09
    left
    0.09
    ,left
    0.09
    Activations Density 0.023%

    No Known Activations