© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53362
    Prev
    Next
    INDEX
    Explanations

    code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CONTROL
    -0.07
    Standing
    -0.07
    λου
    -0.07
     publisher
    -0.06
    chter
    -0.06
    unner
    -0.06
    square
    -0.06
    pow
    -0.06
     packing
    -0.06
    weakSelf
    -0.06
    POSITIVE LOGITS
     запах
    0.06
    稳
    0.06
    ้านด
    0.06
    ัดส
    0.06
     كس
    0.06
     amat
    0.06
     denomination
    0.06
    แทน
    0.06
     bảo
    0.06
     UIView
    0.06
    Activations Density 0.005%

    No Known Activations