© 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. 11-RESID-POST-AA
    11. 100063
    Prev
    Next
    INDEX
    Explanations

    arti

    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
    CanBe
    -0.07
     compar
    -0.06
    _OUT
    -0.06
    Intro
    -0.06
    .ศ
    -0.06
    022
    -0.06
    .WebServlet
    -0.06
    .review
    -0.06
     textu
    -0.06
    /dashboard
    -0.06
    POSITIVE LOGITS
    ��
    0.08
    bam
    0.07
     Quang
    0.07
     물
    0.07
    öl
    0.07
     ジ
    0.07
    罗斯
    0.06
     كما
    0.06
     durumda
    0.06
     roku
    0.06
    Activations Density 0.034%

    No Known Activations