Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59668
    Prev
    Next
    INDEX
    Explanations

    uff suff

    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
    )){
    -0.07
     Oscar
    -0.07
     déjà
    -0.06
    Fel
    -0.06
    神
    -0.06
    Heap
    -0.06
     Fra
    -0.06
    &id
    -0.06
    503
    -0.06
    deps
    -0.06
    POSITIVE LOGITS
     modelBuilder
    0.07
     توق
    0.07
     Richt
    0.06
     strat
    0.06
    .tip
    0.06
     oci
    0.06
     Took
    0.06
    )initWith
    0.06
    ุร
    0.06
     //////////////////////////////////////////////////////////////////////////
    0.06
    Activations Density 0.008%

    No Known Activations