© 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. 15-RESID-POST-AA
    6. 104887
    Prev
    Next
    INDEX
    Explanations

    analysis

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "data
    -0.07
     Produk
    -0.07
    /product
    -0.07
    oup
    -0.06
     urging
    -0.06
    Mut
    -0.06
    idos
    -0.06
     дис
    -0.06
     Pru
    -0.06
              ↵
    -0.06
    POSITIVE LOGITS
    asterxml
    0.06
    谓
    0.06
    ẵn
    0.06
    ANCH
    0.06
     податков
    0.06
    ματα
    0.06
     paddingLeft
    0.06
    лен
    0.06
    igator
    0.06
    μι
    0.06
    Activations Density 0.004%

    No Known Activations