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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 61201
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Feng
    -0.06
     разработ
    -0.06
    recision
    -0.06
     Produk
    -0.06
     다
    -0.06
    _cod
    -0.06
     لأ
    -0.06
     invalidated
    -0.06
    оти
    -0.06
     corrosion
    -0.06
    POSITIVE LOGITS
    ћ
    0.07
    Luckily
    0.07
     करक
    0.06
    стре
    0.06
    aimassage
    0.06
     tempting
    0.06
     toArray
    0.06
    process
    0.06
    reuse
    0.06
    bruar
    0.06
    Activations Density 0.485%

    No Known Activations