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. 7-RESID-POST-AA
    6. 128376
    Prev
    Next
    INDEX
    Explanations

    supply

    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
     کوت
    -0.07
    logan
    -0.07
    ätze
    -0.07
    ensitive
    -0.07
    lední
    -0.07
     kicker
    -0.07
     Cohen
    -0.07
     endpoint
    -0.07
    cene
    -0.07
     ژانویه
    -0.07
    POSITIVE LOGITS
     supply
    0.17
     Supply
    0.14
    Supply
    0.13
    supply
    0.13
     Supplies
    0.12
     supplies
    0.12
     supplying
    0.11
     supplied
    0.11
     suppliers
    0.10
     supplier
    0.10
    Activations Density 0.015%

    No Known Activations