© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 51211
    Prev
    Next
    INDEX
    Explanations

    web development

    np_max-act · gemini-2.0-flash

    meta-instructional directives about how to perform or format a task (e.g., requests to search, generate, or follow a specified response format).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ande
    -0.06
    _ord
    -0.06
     trace
    -0.06
    omba
    -0.06
    constexpr
    -0.06
    真正
    -0.06
     vul
    -0.06
    _clr
    -0.06
    shader
    -0.06
    UMB
    -0.06
    POSITIVE LOGITS
    ông
    0.07
    оу
    0.07
     accus
    0.07
     még
    0.07
    sın
    0.07
     florida
    0.07
    uplicate
    0.06
     Nevertheless
    0.06
    nin
    0.06
    setData
    0.06
    Activations Density 0.481%

    No Known Activations