© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    experiment

    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
     Closure
    -0.08
     seating
    -0.07
     Rate
    -0.07
     leasing
    -0.06
     pcl
    -0.06
     faction
    -0.06
     організа
    -0.06
     Reco
    -0.06
     rocker
    -0.06
     coercion
    -0.06
    POSITIVE LOGITS
     experiment
    0.09
     experiments
    0.09
    periments
    0.08
    periment
    0.08
     estoy
    0.08
    原
    0.08
    하기
    0.08
     experimented
    0.08
    الم
    0.08
    .events
    0.08
    Activations Density 0.013%

    No Known Activations