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. 27-RESID-POST-AA
    6. 9315
    Prev
    Next
    INDEX
    Explanations

    UIKit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    格式
    -0.07
     consoles
    -0.07
    _RESOURCES
    -0.06
     chấp
    -0.06
     Base
    -0.06
    tp
    -0.06
    house
    -0.06
    加载
    -0.06
     commerce
    -0.06
     Hung
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    fon
    0.07
    광역시
    0.07
     statutes
    0.07
    AMI
    0.07
    juries
    0.06
    egot
    0.06
    іїв
    0.06
     PAT
    0.06
     mono
    0.06
    Activations Density 0.001%

    No Known Activations