© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 93699
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    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
     cash
    -0.07
    .emf
    -0.07
     substantially
    -0.06
     café
    -0.06
     testing
    -0.06
    ек
    -0.06
     Reach
    -0.06
     Welch
    -0.06
    grab
    -0.06
     reach
    -0.06
    POSITIVE LOGITS
    _IRQn
    0.06
    StoryboardSegue
    0.06
     passphrase
    0.06
     усп
    0.06
    いや
    0.06
    /oauth
    0.06
    วโม
    0.06
     getUsername
    0.06
    (minutes
    0.06
     بالق
    0.06
    Activations Density 0.923%

    No Known Activations