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. 50828
    Prev
    Next
    INDEX
    Explanations

    expenses and costs

    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
    istr
    -0.07
    Prot
    -0.07
    Pk
    -0.06
    ne
    -0.06
    .addWidget
    -0.06
    adığ
    -0.06
     bids
    -0.06
    Short
    -0.06
    -colored
    -0.06
    (shift
    -0.06
    POSITIVE LOGITS
    _HAL
    0.07
     DEN
    0.06
    rig
    0.06
     ‪
    0.06
     السعودية
    0.06
     гра
    0.06
     CRT
    0.06
     parach
    0.06
    	
    ↵
    0.06
    МО
    0.06
    Activations Density 0.024%

    No Known Activations