© 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. 19-RESID-POST-AA
    6. 84661
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Atlas
    -0.07
    ebra
    -0.07
     бл
    -0.07
    чат
    -0.07
     フ
    -0.07
    頭
    -0.06
     весь
    -0.06
    配
    -0.06
    有些
    -0.06
     quality
    -0.06
    POSITIVE LOGITS
     spit
    0.07
    Movement
    0.06
     Garn
    0.06
     dokun
    0.06
    DISPLAY
    0.06
    persistent
    0.06
    LANGUAGE
    0.06
    /ng
    0.06
     skincare
    0.06
     IntPtr
    0.06
    Activations Density 0.000%

    No Known Activations