© 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. 7-RESID-POST-AA
    11. 92147
    Prev
    Next
    INDEX
    Explanations

    entities

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinnacle
    -0.07
    ifikace
    -0.06
     withObject
    -0.06
     soruml
    -0.06
    ServiceImpl
    -0.06
     barracks
    -0.06
     количества
    -0.06
     moduleName
    -0.06
     чин
    -0.06
     před
    -0.06
    POSITIVE LOGITS
     Forced
    0.06
    Cell
    0.06
    ग
    0.06
    -find
    0.06
    be
    0.06
     fleeting
    0.06
    はない
    0.06
    resher
    0.06
    rai
    0.06
     GWei
    0.06
    Activations Density 0.133%

    No Known Activations