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. 15-RESID-POST-AA
    6. 61108
    Prev
    Next
    INDEX
    Explanations

    museum exhibits and transportation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionResult
    -0.07
     Priority
    -0.07
    公式
    -0.06
    総
    -0.06
    ERCHANTABILITY
    -0.06
     ISC
    -0.06
    Combined
    -0.06
    Priority
    -0.06
    ()">
    -0.06
    @yahoo
    -0.06
    POSITIVE LOGITS
     Tan
    0.06
     Ban
    0.06
    ạo
    0.06
    육
    0.06
     cud
    0.06
    §
    0.06
     uch
    0.06
     assort
    0.06
    .Blue
    0.06
    權
    0.06
    Activations Density 0.034%

    No Known Activations