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. 15-RESID-POST-AA
    6. 74621
    Prev
    Next
    INDEX
    Explanations

    Data rows

    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
     UFO
    -0.06
     contain
    -0.06
    �
    -0.06
     loan
    -0.05
    WIN
    -0.05
     двох
    -0.05
    Contained
    -0.05
    .Format
    -0.05
    818
    -0.05
    asu
    -0.05
    POSITIVE LOGITS
    preserve
    0.07
    Precio
    0.07
     maternity
    0.07
    _GREEN
    0.07
     Giám
    0.07
    造成
    0.07
     뒤
    0.07
    clean
    0.07
     clamp
    0.07
     transplantation
    0.07
    Activations Density 0.021%

    No Known Activations