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. 19-RESID-POST-AA
    6. 127448
    Prev
    Next
    INDEX
    Explanations

    Research/scientific publication text

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Automated
    -0.07
     Bry
    -0.07
     jenis
    -0.06
     accelerated
    -0.06
    Penn
    -0.06
    UCK
    -0.06
    ulp
    -0.06
     Wear
    -0.06
    ":[{"
    -0.06
    Prince
    -0.06
    POSITIVE LOGITS
                                  ↵
    0.07
    .Sort
    0.06
                                   ↵
    0.06
    静
    0.06
    .issue
    0.06
     router
    0.06
    aphrag
    0.06
    osate
    0.06
    <View
    0.06
    .include
    0.06
    Activations Density 0.143%

    No Known Activations