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. 19-RESID-POST-AA
    6. 27468
    Prev
    Next
    INDEX
    Explanations

    News and legal text

    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
    !';↵
    -0.06
     trump
    -0.06
     woo
    -0.06
    आप
    -0.06
     نح
    -0.06
    romosome
    -0.06
     redistribution
    -0.06
     силы
    -0.06
     mee
    -0.06
    定的
    -0.06
    POSITIVE LOGITS
     McC
    0.07
     Frankie
    0.06
    [ii
    0.06
     Workplace
    0.06
    фик
    0.06
    (This
    0.06
    �
    0.06
    mnt
    0.06
     spotřeb
    0.06
    .Millisecond
    0.06
    Activations Density 0.000%

    No Known Activations