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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10728
    Prev
    Next
    INDEX
    Explanations

    meiosis

    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
     urg
    -0.06
     Hra
    -0.06
     Hung
    -0.06
     jednoho
    -0.06
     Cumhurbaş
    -0.06
     одним
    -0.06
     ampl
    -0.06
     जनवर
    -0.06
    χεδόν
    -0.06
     يناير
    -0.06
    POSITIVE LOGITS
     mặc
    0.06
     notes
    0.06
     Decrypt
    0.06
    .Contains
    0.06
    _period
    0.06
    傳
    0.06
    akhir
    0.06
    �数
    0.06
    ,node
    0.06
     update
    0.06
    Activations Density 0.038%

    No Known Activations