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. 52398
    Prev
    Next
    INDEX
    Explanations

    's

    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
    раз
    -0.06
    /../
    -0.06
     memiliki
    -0.06
    ?,?,?,?,
    -0.06
     تم
    -0.06
     sexo
    -0.06
     undef
    -0.06
     subcontract
    -0.06
     Cumhuriyet
    -0.06
     GI
    -0.06
    POSITIVE LOGITS
    (locale
    0.07
    -too
    0.07
    .Decode
    0.07
     initialise
    0.06
     val
    0.06
     purified
    0.06
     Meredith
    0.06
    mental
    0.06
     impaired
    0.06
     powers
    0.06
    Activations Density 0.028%

    No Known Activations