© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34050
    Prev
    Next
    INDEX
    Explanations

    County

    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
     registry
    -0.06
    .Sockets
    -0.06
     ко
    -0.06
     Wir
    -0.06
     Identity
    -0.06
     října
    -0.06
     ölüm
    -0.06
    บอล
    -0.06
     naz
    -0.06
     Compact
    -0.06
    POSITIVE LOGITS
    ービス
    0.07
    enerating
    0.06
    )').
    0.06
    agement
    0.06
    уда
    0.06
    fdf
    0.06
     welding
    0.06
     containerView
    0.06
     sift
    0.06
    _transactions
    0.06
    Activations Density 0.306%

    No Known Activations