© 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
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 123244
    Prev
    Next
    INDEX
    Explanations

    ifying

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <table
    -0.07
    831
    -0.07
    832
    -0.06
    D
    -0.06
    ROUND
    -0.06
    Christmas
    -0.06
    Đây
    -0.06
    řila
    -0.06
    럭
    -0.06
     register
    -0.06
    POSITIVE LOGITS
    ifying
    0.10
    pty
    0.07
     clarified
    0.07
    \.
    0.07
    近
    0.06
    ifies
    0.06
     lymph
    0.06
    xy
    0.06
     낮
    0.06
    私
    0.06
    Activations Density 0.006%

    No Known Activations