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. 123151
    Prev
    Next
    INDEX
    Explanations

    differences

    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
     FPGA
    -0.07
    Tax
    -0.07
    .Fragment
    -0.06
     Ele
    -0.06
     tragedy
    -0.06
     handle
    -0.06
    IVE
    -0.06
    WillAppear
    -0.06
     holes
    -0.06
     Comes
    -0.06
    POSITIVE LOGITS
     xây
    0.07
     نويسنده
    0.07
    .EVT
    0.07
    ีน
    0.06
     všechny
    0.06
    mn
    0.06
    .tex
    0.06
    							 
    0.06
    WIN
    0.06
    �
    0.06
    Activations Density 0.065%

    No Known Activations