© 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. 19-RESID-POST-AA
    6. 72713
    Prev
    Next
    INDEX
    Explanations

    future research

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Seq
    -0.06
     Economics
    -0.06
     telefono
    -0.06
     Liberty
    -0.06
    GRA
    -0.06
     Getting
    -0.06
    CLAIM
    -0.06
     )
    -0.06
     functionName
    -0.06
    ände
    -0.06
    POSITIVE LOGITS
    .equalTo
    0.07
    努力
    0.07
     attributed
    0.06
    (土
    0.06
     ingress
    0.06
     PSU
    0.06
     下跌
    0.06
    сию
    0.06
     الدر
    0.06
     забезпеч
    0.06
    Activations Density 0.039%

    No Known Activations