Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21841
    Prev
    Next
    INDEX
    Explanations

    places

    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
    财
    -0.07
    녁
    -0.07
    δο
    -0.06
    /sec
    -0.06
    identify
    -0.06
    委员
    -0.06
    imal
    -0.06
    參
    -0.06
    Agency
    -0.06
     Ahmad
    -0.06
    POSITIVE LOGITS
     기자
    0.07
     univerz
    0.07
     Pollution
    0.06
    HDATA
    0.06
     Swamp
    0.06
    []={
    0.06
    ağ
    0.06
    ;?>"
    0.06
     اولین
    0.06
     happier
    0.06
    Activations Density 0.153%

    No Known Activations