© 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. 25562
    Prev
    Next
    INDEX
    Explanations

    semi-supervised learning

    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
    -dropdown
    -0.06
    대학
    -0.06
     mik
    -0.06
    hevik
    -0.06
    	protected
    -0.06
    っく
    -0.06
    уру
    -0.06
    яб
    -0.06
     whipped
    -0.05
    oblin
    -0.05
    POSITIVE LOGITS
     InputStreamReader
    0.07
     Vienna
    0.07
     docs
    0.07
     Delay
    0.07
     spreads
    0.07
     Essence
    0.07
     LeBron
    0.07
     Cheers
    0.07
     offending
    0.07
    814
    0.07
    Activations Density 0.001%

    No Known Activations