© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52908
    Prev
    Next
    INDEX
    Explanations

    Multiples

    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
     volunt
    -0.07
     анализ
    -0.07
    าหาร
    -0.07
    증금
    -0.07
     Chern
    -0.06
    GORITH
    -0.06
     groups
    -0.06
    ，你
    -0.06
    　ノ
    -0.06
     office
    -0.06
    POSITIVE LOGITS
    (':')[
    0.06
    locate
    0.06
    _BEGIN
    0.06
     trava
    0.06
    .clients
    0.06
    姓
    0.06
     prophecy
    0.06
    аж
    0.06
    يش
    0.06
    _extension
    0.06
    Activations Density 0.005%

    No Known Activations