© 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. 71582
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Cục
    -0.07
     cognition
    -0.06
     baud
    -0.06
     cemetery
    -0.06
    _unc
    -0.06
     Marketing
    -0.06
     Toolbar
    -0.06
    .ToolStripButton
    -0.06
     управління
    -0.06
    寄
    -0.06
    POSITIVE LOGITS
    manage
    0.07
     органі
    0.06
     paperwork
    0.06
     generado
    0.06
     Got
    0.06
     میان
    0.06
    .squeeze
    0.06
    anut
    0.06
    くらい
    0.06
    lette
    0.06
    Activations Density 0.009%

    No Known Activations