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. 110802
    Prev
    Next
    INDEX
    Explanations

    ake

    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
    $product
    -0.06
    orias
    -0.06
     Mahar
    -0.06
    .CONNECT
    -0.06
    .project
    -0.06
     라이
    -0.06
    .TIME
    -0.06
     withd
    -0.06
    งข
    -0.06
    ับม
    -0.06
    POSITIVE LOGITS
    風
    0.07
    ################################################################
    0.07
    Waiting
    0.07
    coder
    0.06
     redeemed
    0.06
     Saving
    0.06
    etection
    0.06
    ocket
    0.06
     Scholars
    0.06
     sex
    0.06
    Activations Density 0.000%

    No Known Activations