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. 93091
    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_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
     phủ
    -0.07
    _OF
    -0.07
     sehr
    -0.07
    (___
    -0.07
    .Firebase
    -0.06
    annah
    -0.06
    鮮
    -0.06
     pollen
    -0.06
    (review
    -0.06
     Marseille
    -0.06
    POSITIVE LOGITS
    ımı
    0.06
     inex
    0.06
    elog
    0.06
     mens
    0.06
    nou
    0.06
     everyday
    0.06
     mtx
    0.06
     ред
    0.06
    το
    0.06
     svg
    0.06
    Activations Density 0.008%

    No Known Activations