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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 122924
    Prev
    Next
    INDEX
    Explanations

    ux

    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
     р
    -0.07
    fund
    -0.07
     furn
    -0.06
    되지
    -0.06
     cor
    -0.06
    -digit
    -0.06
     related
    -0.06
     hva
    -0.06
     Worm
    -0.06
     chaotic
    -0.06
    POSITIVE LOGITS
    ux
    0.29
    aux
    0.24
    UX
    0.22
    ieux
    0.17
    oux
    0.14
    iaux
    0.13
     deux
    0.09
     faux
    0.09
    deaux
    0.08
     vieux
    0.08
    Activations Density 0.006%

    No Known Activations