© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 125817
    Prev
    Next
    INDEX
    Explanations

    account

    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
    851
    -0.08
    56
    -0.07
    850
    -0.07
    77
    -0.07
    686
    -0.07
     mitigation
    -0.07
    266
    -0.07
    长
    -0.07
    89
    -0.07
    907
    -0.07
    POSITIVE LOGITS
     LoginComponent
    0.07
     impair
    0.07
     رح
    0.06
     obchod
    0.06
    (md
    0.06
     marc
    0.06
    олов
    0.06
     Account
    0.06
     accounts
    0.06
    .ver
    0.06
    Activations Density 0.021%

    No Known Activations