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. 7-RESID-POST-AA
    6. 4360
    Prev
    Next
    INDEX
    Explanations

    <head

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.06
     下载
    -0.06
    需要
    -0.06
    ,在
    -0.06
    监听
    -0.06
    全
    -0.06
     crushers
    -0.06
     certainly
    -0.06
    .timezone
    -0.06
     Turn
    -0.06
    POSITIVE LOGITS
    <head
    0.08
     prac
    0.07
     đài
    0.06
     xe
    0.06
    enment
    0.06
     hr
    0.06
    โย
    0.06
     courteous
    0.06
     Professionals
    0.06
    ascending
    0.06
    Activations Density 0.005%

    No Known Activations