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. 110725
    Prev
    Next
    INDEX
    Explanations

    Of

    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
     negotiation
    -0.07
     McCabe
    -0.07
     spend
    -0.06
     CAS
    -0.06
    tak
    -0.06
     endorsements
    -0.06
     srdce
    -0.06
    _bt
    -0.06
     nextState
    -0.06
     STOP
    -0.06
    POSITIVE LOGITS
    िभ
    0.06
     @[
    0.06
     �
    0.06
    (posts
    0.06
    货
    0.06
     hurry
    0.06
    陰
    0.06
    �能
    0.06
    確認
    0.06
    .findAll
    0.06
    Activations Density 0.003%

    No Known Activations