© 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. 96443
    Prev
    Next
    INDEX
    Explanations

    conditions or specifications

    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
    نسية
    -0.07
     Weaver
    -0.07
    ческим
    -0.06
     shoe
    -0.06
    roomId
    -0.06
    yonel
    -0.06
     Hardcore
    -0.06
     then
    -0.06
    .beginTransaction
    -0.06
     zkušen
    -0.06
    POSITIVE LOGITS
    тів
    0.06
     depend
    0.06
     giorno
    0.06
    ุบ
    0.06
    _original
    0.06
     legend
    0.06
    .impl
    0.06
     dao
    0.06
    .pol
    0.06
     representation
    0.06
    Activations Density 0.549%

    No Known Activations