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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 31983
    Prev
    Next
    INDEX
    Explanations

    to

    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
     proficiency
    -0.07
    ६
    -0.07
     Foundation
    -0.07
    _news
    -0.06
     organising
    -0.06
     windowHeight
    -0.06
    Australia
    -0.06
     Technology
    -0.06
     Unlimited
    -0.06
    .)
    -0.06
    POSITIVE LOGITS
     Serialize
    0.06
     몰
    0.06
    .CompareTo
    0.06
    csrf
    0.06
    .splitext
    0.06
     pancreatic
    0.06
     touted
    0.06
     сбор
    0.06
     esc
    0.06
     enctype
    0.05
    Activations Density 0.048%

    No Known Activations