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. 111427
    Prev
    Next
    INDEX
    Explanations

    names

    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
    坐
    -0.07
    Matchers
    -0.06
     бы
    -0.06
     cos
    -0.06
    퓨터
    -0.06
    (cur
    -0.06
    나라
    -0.06
    /bl
    -0.06
     aprender
    -0.06
    痛
    -0.06
    POSITIVE LOGITS
    CellValue
    0.06
    <KeyValuePair
    0.06
    .$.
    0.06
     больш
    0.06
    ávě
    0.06
    .addHandler
    0.06
     ResultSet
    0.06
    Sold
    0.06
    -original
    0.06
     thủy
    0.06
    Activations Density 0.065%

    No Known Activations