© 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. 98040
    Prev
    Next
    INDEX
    Explanations

    unpacking or unwrapping

    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
     winning
    -0.07
     preserving
    -0.07
    لف
    -0.07
    ОВ
    -0.07
    执
    -0.06
     recommendation
    -0.06
    (MigrationBuilder
    -0.06
     fries
    -0.06
     soldiers
    -0.06
    ności
    -0.06
    POSITIVE LOGITS
     dispersed
    0.07
    个人
    0.07
    Infinity
    0.06
    個人
    0.06
    بعد
    0.06
    (child
    0.06
     RoutedEventArgs
    0.06
    Legend
    0.06
     unpack
    0.06
    eyes
    0.06
    Activations Density 0.136%

    No Known Activations