© 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. 70557
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    _GRID
    -0.06
    闻
    -0.06
    oreal
    -0.06
    .Comment
    -0.06
    经过
    -0.06
    ativní
    -0.06
     answers
    -0.06
    MONTH
    -0.06
    adle
    -0.06
     motiv
    -0.06
    POSITIVE LOGITS
     satın
    0.06
    Jon
    0.06
    erah
    0.06
     AJAX
    0.06
    "context
    0.06
     azt
    0.06
    emean
    0.06
     ApplicationRecord
    0.06
    �
    0.06
     통
    0.06
    Activations Density 0.187%

    No Known Activations