© 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. 15-RESID-POST-AA
    11. 100158
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Athe
    -0.07
    一级
    -0.06
     männ
    -0.06
     nurture
    -0.06
     steht
    -0.06
    ляться
    -0.06
    “The
    -0.06
    阶
    -0.06
    iyatı
    -0.06
     شکن
    -0.06
    POSITIVE LOGITS
    ard
    0.06
    alla
    0.06
    !")
    0.06
     ($.
    0.06
    rick
    0.06
    ARD
    0.06
    oured
    0.06
    .future
    0.06
     Coupe
    0.06
     reported
    0.06
    Activations Density 0.011%

    No Known Activations