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. 7-RESID-POST-AA
    6. 93479
    Prev
    Next
    INDEX
    Explanations

    %

    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
     Kathleen
    -0.07
    orders
    -0.07
    ucle
    -0.06
    สล
    -0.06
    oken
    -0.06
     Fern
    -0.06
    ussels
    -0.06
    ович
    -0.06
     supplemental
    -0.06
     fund
    -0.06
    POSITIVE LOGITS
    (active
    0.07
    \Product
    0.06
    .ARR
    0.06
    aed
    0.06
    소개
    0.06
     тепло
    0.06
     nuest
    0.06
    /swagger
    0.06
    /Common
    0.06
     **************************************************************************
    0.06
    Activations Density 0.012%

    No Known Activations