© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 37728
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
     wurde
    -0.07
    攻击
    -0.06
     serait
    -0.06
     wurden
    -0.06
    Exchange
    -0.06
    AAD
    -0.06
     energia
    -0.06
    Proj
    -0.06
    /runtime
    -0.06
    ριο
    -0.06
    POSITIVE LOGITS
    =item
    0.07
     aç
    0.07
    _OPTIONS
    0.07
     doctors
    0.07
     ($)
    0.06
    (EXIT
    0.06
    bove
    0.06
     modelBuilder
    0.06
    ("./
    0.06
    .executeUpdate
    0.06
    Activations Density 0.006%

    No Known Activations