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. 3-RESID-POST-AA
    6. 122466
    Prev
    Next
    INDEX
    Explanations

    theater productions

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doi
    -0.07
    (st
    -0.07
    .prepend
    -0.07
    (Function
    -0.06
     方法
    -0.06
    Tickets
    -0.06
     Lift
    -0.06
    (job
    -0.06
    (student
    -0.06
     Spain
    -0.06
    POSITIVE LOGITS
    关于
    0.07
    //--------------------------------------------------------------↵
    0.06
    аб
    0.06
    三三
    0.06
    �
    0.06
     wielding
    0.06
    �
    0.06
     Depths
    0.06
    posable
    0.06
    arms
    0.06
    Activations Density 0.233%

    No Known Activations