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. 60901
    Prev
    Next
    INDEX
    Explanations

    Politeness and instructions

    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
    (region
    -0.07
     되었
    -0.07
    하지만
    -0.07
    าศาสตร
    -0.06
     довольно
    -0.06
    	snprintf
    -0.06
     údajů
    -0.06
    -ms
    -0.06
    왔
    -0.06
    Thêm
    -0.06
    POSITIVE LOGITS
    ्ग
    0.07
     kvinn
    0.06
     teammate
    0.06
     chief
    0.06
     AL
    0.06
    Override
    0.06
    	RTDBG
    0.06
    	AL
    0.06
    hi
    0.06
     midd
    0.06
    Activations Density 0.003%

    No Known Activations