© 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. 27-RESID-POST-AA
    11. 20854
    Prev
    Next
    INDEX
    Explanations

    shipping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     premium
    -0.07
    _nonce
    -0.07
     onCreateView
    -0.07
    _return
    -0.06
    ер
    -0.06
    .prev
    -0.06
    _picker
    -0.06
     κρα
    -0.06
    Bar
    -0.06
     erkek
    -0.06
    POSITIVE LOGITS
     tisk
    0.07
    (from
    0.07
    umps
    0.07
    QQ
    0.06
     транспорт
    0.06
     TMZ
    0.06
    Blocking
    0.06
     otel
    0.06
    As
    0.06
     MYSQL
    0.06
    Activations Density 0.063%

    No Known Activations