© 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. 3-RESID-POST-AA
    11. 121828
    Prev
    Next
    INDEX
    Explanations

    :

    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
    .di
    -0.06
    جات
    -0.06
     соблюд
    -0.06
    キャ
    -0.06
    /doc
    -0.06
    -marker
    -0.06
     dataType
    -0.06
    ادة
    -0.06
    只有
    -0.06
     approval
    -0.06
    POSITIVE LOGITS
    _ES
    0.07
    ginas
    0.06
    これ
    0.06
     알아
    0.06
    ONO
    0.06
    onavir
    0.06
     LEN
    0.06
    Campo
    0.06
     Asheville
    0.06
    .an
    0.06
    Activations Density 0.035%

    No Known Activations