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. 11-RESID-POST-AA
    6. 123133
    Prev
    Next
    INDEX
    Explanations

    Number rounding

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Women
    -0.07
    意义
    -0.06
    身体
    -0.06
    ulnerable
    -0.06
    Thirty
    -0.06
    进一步
    -0.06
    -cycle
    -0.06
     Pal
    -0.06
     valuable
    -0.06
    ’.↵↵
    -0.06
    POSITIVE LOGITS
    ]=>
    0.07
     zal
    0.07
     비
    0.07
     RUN
    0.06
    _PROC
    0.06
     Intelli
    0.06
    _cod
    0.06
    .dtd
    0.06
    _GRE
    0.06
     loaded
    0.06
    Activations Density 0.020%

    No Known Activations