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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-RESID-POST-AA
    6. 40648
    Prev
    Next
    INDEX
    Explanations

    API calls and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    建
    -0.06
    ��
    -0.06
     vielen
    -0.06
    Mic
    -0.06
     sabah
    -0.06
     enormous
    -0.06
    ↵↵↵↵↵↵↵↵↵
    -0.06
     Iranian
    -0.06
    řej
    -0.06
     上海
    -0.06
    POSITIVE LOGITS
    .getBody
    0.06
    ヽ
    0.06
     Tỉnh
    0.06
    Symfony
    0.06
    واز
    0.06
    .em
    0.06
    _front
    0.06
    ollect
    0.06
     Collector
    0.06
       
    0.06
    Activations Density 0.008%

    No Known Activations