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. 15-RESID-POST-AA
    6. 80771
    Prev
    Next
    INDEX
    Explanations

    Python libraries

    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
    Attr
    -0.06
     Sellers
    -0.06
    whelming
    -0.06
    =yes
    -0.06
     sql
    -0.06
     Tasmania
    -0.06
     Dear
    -0.06
    	Service
    -0.06
    emails
    -0.06
    	mc
    -0.06
    POSITIVE LOGITS
    ((&___
    0.07
     جزء
    0.07
     другими
    0.06
    redirectToRoute
    0.06
    관리자
    0.06
     مقر
    0.06
    최고
    0.06
    权
    0.06
    μενη
    0.06
     renov
    0.06
    Activations Density 0.033%

    No Known Activations