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. 81019
    Prev
    Next
    INDEX
    Explanations

    1

    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
    goods
    -0.06
    628
    -0.06
     شامل
    -0.06
    ("/
    -0.06
     getApp
    -0.06
     což
    -0.06
    -ST
    -0.06
     Paginator
    -0.06
     MPEG
    -0.06
     чет
    -0.06
    POSITIVE LOGITS
    zsche
    0.06
     Fury
    0.06
    war
    0.06
     substituted
    0.06
    ="'.
    0.06
    gressive
    0.06
     Montana
    0.06
    illegal
    0.06
     Advances
    0.06
     furnished
    0.06
    Activations Density 0.038%

    No Known Activations