© 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. 70959
    Prev
    Next
    INDEX
    Explanations

    "patch" or "repair"

    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
    рап
    -0.07
    rosso
    -0.07
     exile
    -0.06
     introdu
    -0.06
    า
    -0.06
    мель
    -0.06
    Val
    -0.06
     effectively
    -0.06
     slightly
    -0.06
     boutique
    -0.06
    POSITIVE LOGITS
     redund
    0.07
     dalle
    0.07
    erialized
    0.06
    upport
    0.06
     __________________
    0.06
     віднов
    0.06
    _processors
    0.06
    495
    0.06
     ipv
    0.06
     TObject
    0.06
    Activations Density 0.039%

    No Known Activations