© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 77828
    Prev
    Next
    INDEX
    Explanations

    License plates on vehicles

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regina
    -0.06
    번
    -0.06
     Colony
    -0.06
     Kemp
    -0.06
     eased
    -0.06
     bomber
    -0.06
     kir
    -0.06
     setC
    -0.06
     nickel
    -0.06
    QL
    -0.06
    POSITIVE LOGITS
    -FIRST
    0.08
    (Class
    0.07
     tartış
    0.06
    -unstyled
    0.06
    oglob
    0.06
    'field
    0.06
     「
    0.06
    -ra
    0.06
     yapacak
    0.06
    .split
    0.06
    Activations Density 0.005%

    No Known Activations