© 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. 19-RESID-POST-AA
    11. 84593
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     santa
    -0.07
    (player
    -0.07
    Stat
    -0.06
     дал
    -0.06
     ›
    -0.06
     cops
    -0.06
     brand
    -0.06
     coin
    -0.06
    _vm
    -0.06
     Anthrop
    -0.06
    POSITIVE LOGITS
    ổi
    0.07
    ออก
    0.07
    ption
    0.07
    няття
    0.07
    entrada
    0.06
     　　　　　　　　　
    0.06
    ementia
    0.06
    EXPORT
    0.06
    _imag
    0.06
     cushion
    0.06
    Activations Density 0.044%

    No Known Activations