© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 59106
    Prev
    Next
    INDEX
    Explanations

    har

    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
    iciente
    -0.07
     truthful
    -0.07
    ności
    -0.06
    िक
    -0.06
    .firstname
    -0.06
    冊
    -0.06
     �
    -0.06
     ž
    -0.06
    nie
    -0.06
     pessoas
    -0.06
    POSITIVE LOGITS
     Thiên
    0.07
     gió
    0.07
    295
    0.06
    @Resource
    0.06
    ergency
    0.06
    عی
    0.06
    frontend
    0.06
    .Dialog
    0.06
     Kurds
    0.06
     공격
    0.06
    Activations Density 0.013%

    No Known Activations