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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80630
    Prev
    Next
    INDEX
    Explanations

    -treated

    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
    ومات
    -0.07
    ого
    -0.07
     GIF
    -0.07
    28
    -0.06
    文化
    -0.06
     вол
    -0.06
    加载
    -0.06
    ังกล
    -0.06
     domingo
    -0.06
    NX
    -0.06
    POSITIVE LOGITS
     sparing
    0.06
    -us
    0.06
    LONG
    0.06
     hears
    0.06
     Vas
    0.06
     SAS
    0.06
    _RATIO
    0.06
    Want
    0.06
    _ALIGN
    0.06
     чим
    0.06
    Activations Density 0.028%

    No Known Activations