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. 109082
    Prev
    Next
    INDEX
    Explanations

    block

    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
     captive
    -0.07
    ividual
    -0.07
    anner
    -0.07
     bitterness
    -0.06
    Intl
    -0.06
    FTP
    -0.06
     Ore
    -0.06
    acking
    -0.06
    '
    -0.06
     Fre
    -0.06
    POSITIVE LOGITS
    ۲۹
    0.07
    -condition
    0.07
    (unit
    0.06
     Wonder
    0.06
    objectManager
    0.06
     продукції
    0.06
    Blocks
    0.06
    olithic
    0.06
    zos
    0.06
     Jama
    0.06
    Activations Density 0.004%

    No Known Activations