Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 40972
    Prev
    Next
    INDEX
    Explanations

    reading

    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
    oidal
    -0.07
     androidx
    -0.07
     этом
    -0.07
    Manchester
    -0.06
     disagreements
    -0.06
     詳細
    -0.06
     всего
    -0.06
    563
    -0.06
    Webpack
    -0.06
    ‡
    -0.06
    POSITIVE LOGITS
    _dims
    0.07
     pits
    0.07
     Buch
    0.07
     migr
    0.07
    .group
    0.07
    ッツ
    0.06
     getS
    0.06
     persu
    0.06
    <b
    0.06
     获取
    0.06
    Activations Density 0.003%

    No Known Activations