© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 40261
    Prev
    Next
    INDEX
    Explanations

    surprise

    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
     Historic
    -0.07
     stehen
    -0.06
    LEC
    -0.06
     Arduino
    -0.06
    spot
    -0.06
     chocol
    -0.06
    ::*
    -0.06
     =>
    ↵
    -0.06
    .Control
    -0.06
     поль
    -0.06
    POSITIVE LOGITS
     визнач
    0.07
    .tagName
    0.07
    错误
    0.07
    名
    0.06
     hát
    0.06
    ágina
    0.06
     زیبا
    0.06
     венти
    0.06
     state
    0.06
    asaki
    0.06
    Activations Density 0.000%

    No Known Activations