© 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. 11-RESID-POST-AA
    6. 76731
    Prev
    Next
    INDEX
    Explanations

    dated

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .large
    -0.07
     UserRole
    -0.07
    gross
    -0.07
    slash
    -0.06
    braco
    -0.06
     elgg
    -0.06
     orc
    -0.06
    iator
    -0.06
    itor
    -0.06
     narrator
    -0.06
    POSITIVE LOGITS
     dated
    0.07
     дух
    0.06
     TR
    0.06
    ,vector
    0.06
    -value
    0.06
     ages
    0.06
     derechos
    0.06
    Declare
    0.06
    DR
    0.06
    остей
    0.06
    Activations Density 0.002%

    No Known Activations