© 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. 49880
    Prev
    Next
    INDEX
    Explanations

    people in organizations

    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
    (indexPath
    -0.07
    -gun
    -0.07
    \Http
    -0.07
     tả
    -0.07
    胸
    -0.07
    拳
    -0.07
    된다
    -0.06
    숙
    -0.06
     MK
    -0.06
     encode
    -0.06
    POSITIVE LOGITS
     consulta
    0.06
     　　　　　　　　　　　
    0.06
    ĩnh
    0.06
    implicitly
    0.05
     incorpor
    0.05
    etler
    0.05
    neo
    0.05
     Declarations
    0.05
     بالإ
    0.05
     northeastern
    0.05
    Activations Density 0.063%

    No Known Activations