© 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. 52679
    Prev
    Next
    INDEX
    Explanations

    email correspondence

    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
    (animated
    -0.06
    pytest
    -0.06
    Af
    -0.06
     Mahar
    -0.06
    Moh
    -0.06
    .mon
    -0.06
     data
    -0.06
    -use
    -0.06
    тів
    -0.06
     scen
    -0.06
    POSITIVE LOGITS
    operator
    0.07
     intellectually
    0.06
    (form
    0.06
     "->
    0.06
    ickness
    0.06
     Received
    0.06
     ";
    0.06
     gboolean
    0.06
    zzarella
    0.06
     dolayı
    0.06
    Activations Density 0.007%

    No Known Activations