© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 57393
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     wreckage
    -0.07
    /month
    -0.07
    song
    -0.06
    .Ok
    -0.06
    _equ
    -0.06
    ==='
    -0.06
    =center
    -0.06
    -[
    -0.06
    .tabPage
    -0.06
    -collapse
    -0.06
    POSITIVE LOGITS
    ISH
    0.06
     Theft
    0.06
    acing
    0.06
    沖
    0.06
     떨어
    0.06
    STS
    0.06
    Future
    0.06
     bursts
    0.06
     MenuItem
    0.06
     متوسط
    0.06
    Activations Density 0.005%

    No Known Activations