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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 37757
    Prev
    Next
    INDEX
    Explanations

    certified

    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
     nhằm
    -0.08
     Spiele
    -0.07
     Local
    -0.07
    (ob
    -0.07
    /os
    -0.06
     mansion
    -0.06
     Lunch
    -0.06
     Dark
    -0.06
    Developer
    -0.06
     lamp
    -0.06
    POSITIVE LOGITS
     certified
    0.07
     accredited
    0.06
     allied
    0.06
     Monter
    0.06
     certif
    0.06
     //!↵
    0.06
    ata
    0.06
     -.
    0.06
    ised
    0.06
    .func
    0.06
    Activations Density 0.025%

    No Known Activations