Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77491
    Prev
    Next
    INDEX
    Explanations

    quick response

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ills
    -0.06
     Acer
    -0.06
    โลก
    -0.06
     ActiveSupport
    -0.06
    竹
    -0.06
     OPERATION
    -0.06
    .optional
    -0.06
    AP
    -0.06
     inexpensive
    -0.06
    (describing
    -0.06
    POSITIVE LOGITS
     //*
    0.08
     studio
    0.06
     szy
    0.06
    fik
    0.06
     сфер
    0.06
    _Category
    0.06
    Ian
    0.06
    resents
    0.06
    Studio
    0.06
     email
    0.06
    Activations Density 0.055%

    No Known Activations